© 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. 94888
    Prev
    Next
    INDEX
    Explanations

    politics, predictions, actions

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

    illegal activity or laws

    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
     Spirit
    0.45
     Wap
    0.45
     K
    0.43
    igts
    0.43
     tre
    0.42
    i
    0.41
     Inter
    0.41
    clientWidth
    0.41
     Historia
    0.41
     Met
    0.41
    POSITIVE LOGITS
     уйнау
    0.49
     કરવું
    0.49
    ങ്ങൾ
    0.49
    อาจ
    0.48
    矯
    0.48
     کردن
    0.47
    تان
    0.47
     پیروی
    0.47
     бара
    0.47
     отделение
    0.47
    Activations Density 0.000%

    No Known Activations