© 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. 26476
    Prev
    Next
    INDEX
    Explanations

    method calls and functions

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

    programming initialization methods

    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
    وك
    0.45
    ಿಲ್ಲ
    0.43
    Controlled
    0.43
     wafers
    0.42
    וק
    0.42
    лл
    0.42
    华
    0.42
    Oke
    0.41
    ামি
    0.40
    ুখ
    0.40
    POSITIVE LOGITS
     constat
    0.45
     sonrası
    0.45
     കണ്ടെ
    0.44
     ಏಕೆಂದರೆ
    0.44
     sorprend
    0.43
    陛
    0.43
     sırasında
    0.43
     カップ
    0.43
     ಕಂಡ
    0.42
     confirmó
    0.42
    Activations Density 0.000%

    No Known Activations