© 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. 107120
    Prev
    Next
    INDEX
    Explanations

    code, data, or structured text start

    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
     laurent
    -0.75
     boucle
    -0.69
    TRAS
    -0.69
     Pockets
    -0.69
     getPath
    -0.69
    zil
    -0.69
     نار
    -0.68
    progressDialog
    -0.68
    Operational
    -0.67
     Pert
    -0.67
    POSITIVE LOGITS
     publicada
    0.83
     editorial
    0.82
     watercolour
    0.82
     XML
    0.81
     luoghi
    0.79
     passage
    0.79
     scholars
    0.79
    Basel
    0.79
     grabación
    0.79
    setArguments
    0.78
    Activations Density 0.031%

    No Known Activations