© 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. 232228
    Prev
    Next
    INDEX
    Explanations

    colors, spectrum, colored

    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
    Moving
    0.47
    Analyze
    0.47
    자동차
    0.46
    Indianapolis
    0.45
    Trim
    0.44
    Interview
    0.44
    و
    0.44
    Prosecutors
    0.44
    ܣ
    0.44
    andinavian
    0.43
    POSITIVE LOGITS
     oreilles
    0.63
     stripes
    0.51
     aversion
    0.50
     nostrils
    0.49
     límites
    0.49
     creeps
    0.47
     crushes
    0.47
     stripe
    0.46
    सील
    0.46
     industrious
    0.45
    Activations Density 0.000%

    No Known Activations