© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71160
    Prev
    Next
    INDEX
    Explanations

    code and configuration

    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
    </i>
    -1.72
    '
    -1.67
    ,
    -1.67
    ↵↵
    -1.54
     at
    -1.52
     for
    -1.44
     '
    -1.41
    ;
    -1.41
    ;
    -1.41
     no
    -1.38
    POSITIVE LOGITS
    スポンサーリンク
    1.65
     theſe
    1.63
    ܆
    1.60
     možnost
    1.59
    utdown
    1.59
    ჻
    1.56
    ξει
    1.55
    甗
    1.53
    edance
    1.52
     dát
    1.51
    Activations Density 0.107%

    No Known Activations