© 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. 31086
    Prev
    Next
    INDEX
    Explanations

    Blokus, testimonials

    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
     tutoring
    -0.78
    딪
    -0.73
     Salary
    -0.71
     EOF
    -0.70
     TABLE
    -0.68
     chanteur
    -0.68
     salary
    -0.68
     encircled
    -0.67
     Axis
    -0.67
    Peng
    -0.67
    POSITIVE LOGITS
     routes
    0.80
    routes
    0.79
     Sider
    0.77
     navegar
    0.74
    煎
    0.74
    MUX
    0.73
     煎
    0.73
    Grüsse
    0.73
    pozdrawiam
    0.72
    体に
    0.71
    Activations Density 0.005%

    No Known Activations