© 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. 102765
    Prev
    Next
    INDEX
    Explanations

    diff lines

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

    the "@@" line markers that indicate line numbers in unified diff format.

    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
    _
    -2.11
     six
    -1.50
     three
    -1.50
     accrued
    -1.47
     thirteen
    -1.43
     touted
    -1.43
     numerous
    -1.38
     two
    -1.35
     provide
    -1.34
     elaborado
    -1.34
    POSITIVE LOGITS
     ۱۵
    1.84
     ۱۶
    1.78
     of
    1.77
    
    1.74
     ۱۸
    1.73
     queste
    1.73
    ౬
    1.72
    廋
    1.68
    4
    1.65
     ۱۱
    1.63
    Activations Density 0.000%

    No Known Activations