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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4468
    Prev
    Next
    INDEX
    Explanations

    multiline strings or code blocks

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

    This neuron tracks affectionate obituary descriptors—words like beloved, loving, dear, cherished, etc., often paired with family roles.

    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
    ی
    0.88
    بیل
    0.81
    持续
    0.79
    获得
    0.74
     волос
    0.73
    其它
    0.72
     élevé
    0.70
    AddTime
    0.70
    tooltip
    0.69
    出售
    0.69
    POSITIVE LOGITS
     निर्देशित
    0.82
     conco
    0.79
    ا
    0.79
     heartwarming
    0.76
    ?!
    0.74
    입니다
    0.74
     garlands
    0.74
     ?!
    0.73
    ።
    0.73
    ኵ
    0.73
    Activations Density 0.004%

    No Known Activations