© 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. 113054
    Prev
    Next
    INDEX
    Explanations

    code structure and fragments

    np_acts-logits-general · gemini-2.5-flash-lite

    structural or formatting characters in code and data files, particularly colons, quotation marks, and tokens that indicate field separators or property definitions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    pulseira
    -1.73
    廡
    -1.71
     teď
    -1.60
     alemanes
    -1.57
    boneca
    -1.51
     how
    -1.50
     teníamos
    -1.46
     compañías
    -1.44
    到这里
    -1.41
    Vendo
    -1.41
    POSITIVE LOGITS
    \
    1.75
                
    1.72
    (
    1.54
        
    1.48
                            
    1.43
    8
    1.38
    {
    1.34
    @
    1.32
    [
    1.31
       
    1.29
    Activations Density 0.041%

    No Known Activations