© 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. 31432
    Prev
    Next
    INDEX
    Explanations

    software license and programming libraries

    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
    TimeSpan
    -0.76
    RequestId
    -0.68
     Gibbs
    -0.67
     Profit
    -0.65
     Sheet
    -0.65
    ぶり
    -0.63
    áus
    -0.63
     Chow
    -0.63
     ministers
    -0.62
     бесе
    -0.62
    POSITIVE LOGITS
    mappings
    0.77
     Rubens
    0.75
    barra
    0.73
     verbreitet
    0.72
    zema
    0.71
    weld
    0.69
     Mapp
    0.68
    conium
    0.65
    ntu
    0.63
     twij
    0.63
    Activations Density 0.145%

    No Known Activations