© 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. 107992
    Prev
    Next
    INDEX
    Explanations

    upcoming events and dates

    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
     come
    -0.97
     seres
    -0.93
    PrintWriter
    -0.91
    тербург
    -0.90
     Burton
    -0.86
    Burton
    -0.85
     bonos
    -0.83
     huevos
    -0.83
    above
    -0.82
     grief
    -0.81
    POSITIVE LOGITS
     soon
    1.26
     Soon
    1.10
    Soon
    1.02
    soon
    0.99
     SOON
    0.93
    seu
    0.88
     владель
    0.81
     sonnet
    0.81
     Notably
    0.79
    entlichen
    0.79
    Activations Density 0.019%

    No Known Activations