© 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. 57912
    Prev
    Next
    INDEX
    Explanations

    license agreements and disclaimers

    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
    VALOR
    -0.72
    auth
    -0.69
    ComponentModel
    -0.67
    ỗ
    -0.67
    Valor
    -0.66
    Keine
    -0.66
    Ausstattung
    -0.66
    NOTIFY
    -0.66
    eph
    -0.66
    ς
    -0.66
    POSITIVE LOGITS
    ushy
    0.78
     służ
    0.72
     pilgrim
    0.65
    ugian
    0.63
     viaggio
    0.63
     AssertionError
    0.63
    gyp
    0.62
     deutsche
    0.62
    alamualaikum
    0.61
     conservative
    0.61
    Activations Density 0.090%

    No Known Activations