© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 237571
    Prev
    Next
    INDEX
    Explanations

    specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     resistance
    0.46
     call
    0.45
    dir
    0.43
     nonstop
    0.43
    den
    0.42
     G
    0.41
     merciless
    0.41
    call
    0.40
     Call
    0.40
    dc
    0.40
    POSITIVE LOGITS
    সাব
    0.57
     腰
    0.55
    限定
    0.55
    無し
    0.55
     裏
    0.55
     війни
    0.55
    轢
    0.55
     ダイヤモンド
    0.54
     限
    0.54
    ꞎ
    0.54
    Activations Density 0.001%

    No Known Activations