© 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. 26434
    Prev
    Next
    INDEX
    Explanations

    private code keywords

    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
     Heilige
    -1.07
    three
    -1.07
    だそうです
    -0.95
     подходит
    -0.92
    two
    -0.91
     Handeln
    -0.91
    five
    -0.88
     частности
    -0.88
     mediante
    -0.87
     muhte
    -0.87
    POSITIVE LOGITS
    ֠
    1.20
     ANTONIO
    1.19
     misa
    1.18
     destina
    1.14
     tapis
    1.12
     prado
    1.09
     tenis
    1.07
    atecas
    1.05
     Cuer
    1.03
     ovan
    1.03
    Activations Density 0.001%

    No Known Activations