© 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. 10-GEMMASCOPE-RES-131K
    7. 48390
    Prev
    Next
    INDEX
    Explanations

    code context or file paths

    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
    
    -2.63
    
    -2.27
    ఽ
    -2.27
    ཿ
    -2.16
    ཥ
    -2.08
    傒
    -2.08
    憷
    -2.06
    
    -2.03
    瓛
    -2.00
     utiliser
    -1.95
    POSITIVE LOGITS
     at
    2.92
     or
    2.88
     on
    2.66
     Although
    2.42
     in
    2.42
     Despite
    2.33
     While
    2.33
     if
    2.31
    ;
    2.30
     for
    2.11
    Activations Density 0.006%

    No Known Activations