© 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. 35770
    Prev
    Next
    INDEX
    Explanations

    interface or state parameter

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

    arguments in code descriptions

    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
    h
    0.57
    Let
    0.52
    <h5>
    0.50
    coefficient
    0.48
    y
    0.48
    a
    0.48
    Learn
    0.48
    keywords
    0.46
    ⚠️
    0.46
    PROVIDED
    0.46
    POSITIVE LOGITS
     odc
    0.54
     ポー
    0.54
     først
    0.53
     articulo
    0.50
     pierws
    0.49
     jejich
    0.48
     våra
    0.48
     hamburg
    0.48
     jų
    0.48
     tailgate
    0.48
    Activations Density 0.000%

    No Known Activations