© 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. 33799
    Prev
    Next
    INDEX
    Explanations

    modelEL-

    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
    nought
    -1.08
    걍
    -1.06
    ülő
    -1.05
    knapp
    -1.04
    ávajú
    -1.02
    allowing
    -1.02
     rodas
    -1.00
    Soorten
    -0.99
     完了
    -0.99
     pulmon
    -0.98
    POSITIVE LOGITS
     sánh
    1.47
     homicidio
    1.38
     gutem
    1.27
     mikina
    1.19
     кв
    1.13
     möjligt
    1.12
     violación
    1.12
     キング
    1.11
     bör
    1.09
    ]$.
    1.09
    Activations Density 0.049%

    No Known Activations