© 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. 22-GEMMASCOPE-RES-131K
    7. 128285
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and paths

    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_22/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
    serviceWorker
    -1.12
    bakter
    -1.08
    mazing
    -1.08
    ########.
    -1.04
    ##
    -1.03
     sindaco
    -1.03
    umente
    -1.00
    ïc
    -0.99
     のか
    -0.99
    titue
    -0.99
    POSITIVE LOGITS
    那種
    1.00
     fausse
    1.00
     cuánto
    0.99
    就不能
    0.97
     also
    0.95
    хъ
    0.95
     ponownie
    0.92
    豐富
    0.92
    没问题
    0.92
     dernière
    0.91
    Activations Density 0.048%

    No Known Activations