© 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. 77749
    Prev
    Next
    INDEX
    Explanations

    closing tags

    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
    moud
    -0.97
    ЭС
    -0.95
     trás
    -0.94
    ellipsis
    -0.93
     článek
    -0.93
    membered
    -0.93
    coil
    -0.92
    krish
    -0.92
    ícias
    -0.91
    Reilly
    -0.91
    POSITIVE LOGITS
    ero
    1.07
     writer
    1.05
     provider
    0.99
     producer
    0.96
    觊
    0.95
    reiber
    0.94
    ker
    0.94
    られない
    0.94
    inger
    0.93
     dictators
    0.93
    Activations Density 0.127%

    No Known Activations