© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63164
    Prev
    Next
    INDEX
    Explanations

    warranty, Foundation, Scaliola

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***/
    -0.95
    чого
    -0.84
     Albany
    -0.82
     lefs
    -0.81
     briefly
    -0.81
    idamente
    -0.80
    👁
    -0.77
     cetera
    -0.77
     XCTest
    -0.76
    compliant
    -0.75
    POSITIVE LOGITS
     rękaw
    0.83
     exagger
    0.82
    Trabajo
    0.81
    ウェブサイト
    0.81
     감
    0.78
    ⠏
    0.77
    Paquete
    0.76
    impos
    0.75
    armée
    0.75
     degré
    0.74
    Activations Density 0.004%

    No Known Activations