© 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. 243708
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    ಕ
    0.46
     पक्षा
    0.45
     ל
    0.45
     Ass
    0.43
    트
    0.43
    ologically
    0.42
     incongru
    0.42
     הח
    0.42
     mildew
    0.42
     conjectured
    0.41
    POSITIVE LOGITS
     TouchUtils
    0.56
     trueMap
    0.52
    fireFlower
    0.48
     作品
    0.47
    pade
    0.45
    TGFuZ
    0.45
    豆
    0.45
    fang
    0.45
     pokud
    0.44
    माइंडर
    0.44
    Activations Density 0.000%

    No Known Activations