© 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. 66843
    Prev
    Next
    INDEX
    Explanations

    graphics and geometry calculations

    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
    bsen
    -1.41
    ofing
    -1.26
     diseñador
    -1.23
     preferences
    -1.23
    mbal
    -1.18
     keras
    -1.16
    Nederland
    -1.16
     Naturs
    -1.16
     fotógrafo
    -1.15
    })();
    -1.14
    POSITIVE LOGITS
     inapropiados
    0.97
    球队
    0.96
     $\#
    0.95
     vlieg
    0.95
     нарушения
    0.93
    freies
    0.93
     jezelf
    0.92
     metodi
    0.91
     occafion
    0.91
    ƅ
    0.90
    Activations Density 0.022%

    No Known Activations