© 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. 114344
    Prev
    Next
    INDEX
    Explanations

    respectful of, applicable goods, effect result

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

    revolution, reshape, profiles, compression

    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
    Indexing
    0.54
    തിൽ
    0.50
     بلغ
    0.48
    $),
    0.47
     المحلي
    0.46
     critique
    0.45
     condizioni
    0.45
    部分は
    0.45
    |}{
    0.44
     bonito
    0.44
    POSITIVE LOGITS
    र
    0.47
    ધાન
    0.46
    aceous
    0.46
    otide
    0.45
    是要
    0.44
    um
    0.44
    รั
    0.44
     은
    0.43
    प्रेम
    0.43
    你
    0.43
    Activations Density 0.000%

    No Known Activations