© 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. 180828
    Prev
    Next
    INDEX
    Explanations

    perform well

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

    pros and cons

    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
    )，
    0.46
     では
    0.44
    アル
    0.44
    樎
    0.43
    ಟೆ
    0.43
    endige
    0.42
    $),
    0.42
     Forms
    0.42
    ｻ
    0.42
     う
    0.41
    POSITIVE LOGITS
     продаже
    0.55
     démarrage
    0.54
     petits
    0.47
     речи
    0.47
     váy
    0.47
     bán
    0.46
     wirelessly
    0.46
     gros
    0.45
    effects
    0.45
    लाइट
    0.45
    Activations Density 0.000%

    No Known Activations