© 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. 157239
    Prev
    Next
    INDEX
    Explanations

    ordinary means, resolution needed

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

    offensive language and specific names

    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
    م
    0.47
    www
    0.45
    ب
    0.44
    mp
    0.43
    وک
    0.43
    lib
    0.43
    quote
    0.43
    arch
    0.42
    嗯
    0.42
    مند
    0.41
    POSITIVE LOGITS
     meeste
    0.45
     jednou
    0.44
     maioria
    0.44
    гатьох
    0.43
    ющегося
    0.43
     corta
    0.43
     begins
    0.42
     inteiro
    0.41
    AppDesigner
    0.41
     vanlig
    0.41
    Activations Density 0.000%

    No Known Activations