© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11561
    Prev
    Next
    INDEX
    Explanations

    programming comments or metadata

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric tokens (especially numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words or phrases related to involvement or participation, particularly in passive or past tense contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    common function words and basic verbs that structure explanatory or informational prose.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical or administrative terminology and configuration/status keywords within instructional or informational text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ၇
    0.87
     Боль
    0.85
    啶
    0.84
    टना
    0.83
     quintessential
    0.82
    ﺴ
    0.82
     fundamentos
    0.81
    ссив
    0.80
    seeing
    0.80
    止め
    0.79
    POSITIVE LOGITS
     între
    0.73
     veille
    0.73
    ation
    0.72
    ન
    0.70
     and
    0.70
     With
    0.66
     è
    0.65
    る
    0.64
     lì
    0.64
    With
    0.63
    Activations Density 0.000%

    No Known Activations