© 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. 73275
    Prev
    Next
    INDEX
    Explanations

    function calls

    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
     siè
    -2.39
     poë
    -2.11
     faciliter
    -2.11
     attente
    -2.03
    鳚
    -2.02
     inond
    -2.02
    
    -2.00
     bascul
    -1.99
    
    -1.98
     constater
    -1.96
    POSITIVE LOGITS
     an
    2.59
     all
    2.45
     even
    2.31
     both
    2.20
    L
    2.19
     only
    2.17
    ,
    2.08
     that
    2.06
     really
    2.05
    b
    2.05
    Activations Density 0.007%

    No Known Activations