© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13590
    Prev
    Next
    INDEX
    Explanations

    head / heads

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

    The neuron specifically fires on the token “Head” (and its lowercase/heading variants), marking section headings or title labels that begin with “Head.”

    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_31_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
    wristwatch
    0.60
     MPC
    0.59
     Seventeen
    0.54
    挾
    0.54
    reng
    0.53
     AGC
    0.53
     MAM
    0.53
     Porn
    0.52
    குழந்த
    0.52
    ष्णु
    0.52
    POSITIVE LOGITS
     Head
    1.33
    Head
    1.30
     head
    1.23
    顱
    1.23
    頭
    1.23
     হেড
    1.22
     头
    1.22
     ヘッド
    1.19
    头
    1.16
     HEAD
    1.15
    Activations Density 0.094%

    No Known Activations