© 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. 135476
    Prev
    Next
    INDEX
    Explanations

    health, safety, willing, time, movie

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

    code or descriptive processes

    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
     Endocrinology
    0.50
    AMP
    0.49
     İyi
    0.48
     ㅛ
    0.46
     GoObject
    0.46
     Against
    0.45
    abhuto
    0.45
    ATL
    0.44
     ObjData
    0.44
    fread
    0.43
    POSITIVE LOGITS
     at
    0.52
    드로
    0.51
    is
    0.51
    מ
    0.49
    ך
    0.49
     risque
    0.48
     Garmin
    0.48
     més
    0.47
     שי
    0.47
    es
    0.47
    Activations Density 0.001%

    No Known Activations