© 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. 3140
    Prev
    Next
    INDEX
    Explanations

    for loops

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    흰
    0.70
    增
    0.66
    String
    0.65
    string
    0.61
    무
    0.61
    sum
    0.60
    Bud
    0.60
    คิด
    0.60
    KO
    0.59
    Coul
    0.59
    POSITIVE LOGITS
     (;
    0.74
    (;
    0.70
     ポリ
    0.66
     orale
    0.65
     ໜອງ
    0.64
    ករណ៍
    0.63
     スタッドレスタイヤ
    0.63
     Identified
    0.63
     티
    0.63
     POLICY
    0.62
    Activations Density 0.023%

    No Known Activations