© 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. 15039
    Prev
    Next
    INDEX
    Explanations

    locations, distributions, usages, numbers

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

    The neuron is highly sensitive to longer, content-bearing words (e.g. polysyllabic verbs, adjectives, and nouns) in the text.

    oai_token-act-pair · o4-miniTriggered 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
    1.05
    n
    0.77
    zo
    0.74
    ec
    0.69
    -
    0.69
    #
    0.69
    ра
    0.68
    ique
    0.68
    ised
    0.65
    ne
    0.64
    POSITIVE LOGITS
     विभक्ति
    0.99
    Ⅼ
    0.96
    㴓
    0.96
     드
    0.89
    环境下
    0.89
     Вин
    0.89
     Fmat
    0.88
     Andalusia
    0.87
     desarrollo
    0.86
    进度
    0.86
    Activations Density 0.000%

    No Known Activations