© 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. 24365
    Prev
    Next
    INDEX
    Explanations

    geographical or place names

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

    experimentation, effects, unexpected events

    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
    িয়া
    0.50
     пользователя
    0.46
    nitř
    0.45
    āda
    0.45
     Пен
    0.44
    тись
    0.44
    ри
    0.44
    匼
    0.43
     déposer
    0.42
    <unused2116>
    0.42
    POSITIVE LOGITS
     Atlantic
    0.47
    Celsius
    0.46
     Mediterranean
    0.46
     island
    0.45
     alligator
    0.45
    Gal
    0.44
     eel
    0.44
     Nile
    0.44
     guarantor
    0.43
     footnote
    0.43
    Activations Density 0.000%

    No Known Activations