© 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. 237573
    Prev
    Next
    INDEX
    Explanations

    comparisons, ethics, price, performance

    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
     spettac
    0.54
     planche
    0.54
    欽
    0.52
    MARY
    0.50
     bauen
    0.50
     wyk
    0.50
     PARK
    0.50
     peralatan
    0.49
    磨
    0.49
    HEY
    0.49
    POSITIVE LOGITS
    isEmpty
    0.49
    ir
    0.49
     can
    0.48
    ;
    0.46
     complications
    0.45
    如果是
    0.45
    content
    0.45
    ones
    0.45
     information
    0.45
     when
    0.44
    Activations Density 0.000%

    No Known Activations