© 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. 130055
    Prev
    Next
    INDEX
    Explanations

    programming modules and integration

    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
     other
    -1.03
     salão
    -1.02
     these
    -0.97
     this
    -0.94
     adult
    -0.91
     akumulator
    -0.90
     идеально
    -0.90
    odotus
    -0.90
    Santis
    -0.89
    armani
    -0.89
    POSITIVE LOGITS
     адап
    0.93
    Torn
    0.89
    前面
    0.89
    اسپ
    0.87
     ERROR
    0.87
     Фон
    0.87
     integration
    0.87
    ложений
    0.86
     mutat
    0.86
    imą
    0.85
    Activations Density 0.134%

    No Known Activations