© 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. 100146
    Prev
    Next
    INDEX
    Explanations

    code structure elements

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

    indentation or whitespace at the beginning of lines in code, particularly before function parameters or variable declarations.

    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
    pflan
    -1.73
     hant
    -1.69
    🖐
    -1.68
     ſou
    -1.66
     fatale
    -1.60
     rapporter
    -1.59
     etik
    -1.59
     magasiner
    -1.59
    gründ
    -1.59
     postale
    -1.58
    POSITIVE LOGITS
    \
    2.39
     This
    1.75
     who
    1.67
     that
    1.62
     have
    1.59
     can
    1.55
    This
    1.54
     then
    1.48
     You
    1.48
     Fünf
    1.43
    Activations Density 0.007%

    No Known Activations