© 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. 10-GEMMASCOPE-RES-131K
    7. 72616
    Prev
    Next
    INDEX
    Explanations

    file path structures / or other separators

    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_10/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
    ”,
    -1.73
     –
    -1.73
    k
    -1.70
     and
    -1.68
    $
    -1.64
    s
    -1.56
    al
    -1.55
    »;
    -1.55
    。”
    -1.50
    …»
    -1.47
    POSITIVE LOGITS
     búsquedas
    1.56
    kowania
    1.52
     aliados
    1.52
    
    1.49
     espectaculares
    1.49
    larını
    1.46
     estímulo
    1.44
     divertidos
    1.41
    蜴
    1.38
     ursprüng
    1.38
    Activations Density 0.000%

    No Known Activations