© 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. 48678
    Prev
    Next
    INDEX
    Explanations

    Taylor & Francis and Routledge

    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
     derive
    -0.81
    edges
    -0.73
     childcare
    -0.72
     FILTER
    -0.68
    ristas
    -0.68
    babwe
    -0.68
    Funny
    -0.68
     competición
    -0.67
     phong
    -0.66
     ügy
    -0.66
    POSITIVE LOGITS
     Taylor
    1.07
    Taylor
    1.02
    Routledge
    1.02
    tand
    0.96
     Routledge
    0.93
     Informa
    0.89
     TAYLOR
    0.87
    informa
    0.85
    INTE
    0.83
     tand
    0.80
    Activations Density 0.023%

    No Known Activations