© 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. 130721
    Prev
    Next
    INDEX
    Explanations

    space as, all refunds, WiFi is, no support

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

    consequences and effects

    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
     Че
    0.52
    寤
    0.50
     Regul
    0.46
     नहर
    0.45
     Держа
    0.45
     внутреннего
    0.45
     В
    0.45
    ての
    0.44
     высокого
    0.44
    鈳
    0.44
    POSITIVE LOGITS
    /\
    0.46
     original
    0.46
    museum
    0.46
    COPY
    0.44
    Original
    0.43
     copying
    0.43
    ndown
    0.43
    original
    0.43
     foram
    0.43
    nestjs
    0.43
    Activations Density 0.000%

    No Known Activations