© 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. 57670
    Prev
    Next
    INDEX
    Explanations

    Supreme Court proceedings

    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
     Practitioner
    -0.73
    isDebugEnabled
    -0.70
    模特
    -0.68
     jonka
    -0.67
    getOutputStream
    -0.66
     alignItems
    -0.66
     h
    -0.64
     incontri
    -0.64
     Sender
    -0.63
    ızlık
    -0.63
    POSITIVE LOGITS
    🩺
    0.89
     Application
    0.85
    Applications
    0.82
    eterangan
    0.80
    抿
    0.79
     Partai
    0.79
    Application
    0.78
     samostat
    0.78
     constaté
    0.78
    象徴
    0.78
    Activations Density 0.005%

    No Known Activations