© 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. 97322
    Prev
    Next
    INDEX
    Explanations

    building permits

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

    Scar, regions, park, timing, charming

    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
    М
    0.45
    트를
    0.45
     સરકાર
    0.44
    тии
    0.44
    ОР
    0.44
    Л
    0.43
    тріш
    0.43
    붐
    0.43
    벤트
    0.42
     CHAR
    0.42
    POSITIVE LOGITS
    inline
    0.48
    拯
    0.48
    unshift
    0.47
    falling
    0.45
    novel
    0.45
    隷
    0.44
    classic
    0.44
     قادر
    0.43
    corner
    0.43
    os
    0.43
    Activations Density 0.000%

    No Known Activations