© 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. 48657
    Prev
    Next
    INDEX
    Explanations

    copyright and license notices

    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
    Parcelize
    -0.75
    registry
    -0.73
     aula
    -0.71
    ]")
    -0.68
    steve
    -0.67
     nguyên
    -0.67
    录
    -0.67
    $('#
    -0.67
     pantry
    -0.67
     générations
    -0.66
    POSITIVE LOGITS
    Extract
    0.73
     Extract
    0.69
     shaved
    0.66
    feng
    0.65
     chargée
    0.64
    Diction
    0.63
    惚
    0.63
    🌔
    0.63
    NSDictionary
    0.63
     кило
    0.60
    Activations Density 0.092%

    No Known Activations