© 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. 154086
    Prev
    Next
    INDEX
    Explanations

    geographic entities and places

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

    questions and comments

    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
     熱
    0.52
     tí
    0.47
     沒有
    0.47
    ربي
    0.46
     গৌ
    0.46
    ধিক
    0.46
     ञ
    0.46
     ህ
    0.46
    মাত্র
    0.44
     ጉ
    0.44
    POSITIVE LOGITS
     ekonom
    0.50
     labs
    0.49
     alış
    0.49
     sinks
    0.49
     forts
    0.47
    นคร
    0.46
     risk
    0.45
     estuaries
    0.44
     cidades
    0.44
    Nast
    0.44
    Activations Density 0.000%

    No Known Activations