© 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. 56921
    Prev
    Next
    INDEX
    Explanations

    code structure and getters/setters

    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
    éhez
    0.46
    ંને
    0.39
    {\|
    0.38
    යින්
    0.38
    пону
    0.38
    య్య
    0.37
    γκεκρι
    0.37
    湪
    0.37
     Spiegel
    0.37
     понятно
    0.36
    POSITIVE LOGITS
    FROM
    0.45
     protectors
    0.41
    лід
    0.41
    JOUR
    0.41
    Journal
    0.40
    SCALE
    0.40
    パーティ
    0.40
    Fee
    0.39
    فيد
    0.39
    CIF
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.