© 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. 105545
    Prev
    Next
    INDEX
    Explanations

    conditions and terminology

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

    system density letter damage altered structured

    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
    道の
    0.50
    ن
    0.50
    ร้าน
    0.47
    ข้อ
    0.45
    ول
    0.45
    ナ
    0.45
    いで
    0.44
    深入
    0.44
    人は
    0.43
     negozio
    0.43
    POSITIVE LOGITS
     khán
    0.44
     reggae
    0.44
     Scary
    0.43
     Throw
    0.41
     մի
    0.41
     অবশ্য
    0.41
     बसा
    0.41
    组成的
    0.41
     pamię
    0.40
     cực
    0.40
    Activations Density 0.000%

    No Known Activations