© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22324
    Prev
    Next
    INDEX
    Explanations

    unlawful, illegal, improper, wrongful

    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
    parfum
    -1.63
     锅
    -1.45
    юр
    -1.44
     bunda
    -1.35
     only
    -1.29
    Elles
    -1.27
     ہو
    -1.26
    Chaque
    -1.23
    点了
    -1.23
    \
    -1.23
    POSITIVE LOGITS
     similares
    1.45
     otros
    1.41
    がありました
    1.41
     diferentes
    1.38
     the
    1.34
     use
    1.28
     practices
    1.28
     envíos
    1.27
     ちゃん
    1.27
     nuevos
    1.26
    Activations Density 0.071%

    No Known Activations