© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71702
    Prev
    Next
    INDEX
    Explanations

    court case identifiers

    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
    During
    -1.15
     menetap
    -1.12
     that
    -1.12
     {*}
    -1.11
    IQUES
    -1.07
    Étape
    -1.06
     kekasih
    -1.03
    ͼ
    -1.03
    AutoScaleMode
    -1.02
     during
    -1.01
    POSITIVE LOGITS
     commandés
    0.97
    section
    0.91
     rojos
    0.91
    ’
    0.90
    Z
    0.88
     graciosos
    0.86
     vermelhas
    0.84
     competitivos
    0.83
     vendus
    0.81
    谴
    0.81
    Activations Density 0.003%

    No Known Activations