© 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. 10-GEMMASCOPE-RES-131K
    7. 43785
    Prev
    Next
    INDEX
    Explanations

    Huntington, Hancock, Eaton, Boyle

    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_10/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
    section
    -2.98
    ꯱
    -2.69
     Examining
    -2.42
    März
    -2.28
    之后
    -2.23
     Asking
    -2.23
     Representing
    -2.20
    end
    -2.20
     '-';
    -2.16
    !"
    -2.13
    POSITIVE LOGITS
     são
    2.41
     să
    2.31
     firmado
    2.27
    ↵
    2.27
     tomado
    2.22
     elic
    2.20
     unido
    2.20
    猁
    2.17
    ⁕
    2.17
     bestand
    2.16
    Activations Density 0.009%

    No Known Activations