© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10005
    Prev
    Next
    INDEX
    Explanations

    article language

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

    The neuron identifies section headers or links labeled “Questions” (e.g. “other questions,” “related questions”).

    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
     FIX
    0.55
    <unused62>
    0.53
    কম
    0.52
     fix
    0.52
     Passwort
    0.52
     PLC
    0.52
    лят
    0.51
     purity
    0.51
     হবেনা
    0.50
    Filler
    0.50
    POSITIVE LOGITS
    蛞
    0.59
    बिहार
    0.58
    ಇ
    0.56
    vrir
    0.55
    创始
    0.55
    ירים
    0.55
     июня
    0.55
    主题
    0.54
     bylaws
    0.54
    個人
    0.54
    Activations Density 0.000%

    No Known Activations