© 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. 39721
    Prev
    Next
    INDEX
    Explanations

    foreign language words and place names

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

    opportunities and games

    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
     вызыва
    0.52
     অবদান
    0.47
     کنند
    0.45
    )^{*}\
    0.44
     بیٹنگ
    0.44
    ）・
    0.43
    arlene
    0.43
     hypertrophy
    0.43
    үз
    0.43
     отвеча
    0.42
    POSITIVE LOGITS
     Sistema
    0.48
     domestic
    0.47
     relacion
    0.46
     reign
    0.46
     God
    0.46
     SQL
    0.45
     Kapital
    0.45
    咵
    0.45
     Danmark
    0.44
     herman
    0.44
    Activations Density 0.000%

    No Known Activations