© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130246
    Prev
    Next
    INDEX
    Explanations

    NOT followed by word

    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
    髫
    -1.70
     небольшой
    -1.52
    腚
    -1.50
    giarism
    -1.38
    
    -1.35
     ennemis
    -1.34
    mpagne
    -1.30
     semua
    -1.29
    Dalton
    -1.29
    蹑
    -1.27
    POSITIVE LOGITS
    Those
    2.06
    What
    1.98
    There
    1.91
    How
    1.82
    You
    1.81
    One
    1.77
    Other
    1.72
    Making
    1.72
    When
    1.70
    Some
    1.70
    Activations Density 0.035%

    No Known Activations