© 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. 22-GEMMASCOPE-RES-131K
    7. 66005
    Prev
    Next
    INDEX
    Explanations

    virtual single, chemical character

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

    formatting elements and structural markers in news articles and documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    setAlpha
    -1.03
    uttosto
    -1.02
    etah
    -0.99
    
    -0.97
    ävät
    -0.97
     توانند
    -0.96
    ரா
    -0.96
    
    -0.94
     bebé
    -0.94
    西兰
    -0.92
    POSITIVE LOGITS
     his
    1.20
     μεγαλ
    1.02
     show
    0.99
    olkata
    0.96
     even
    0.94
     addirittura
    0.94
     nothwendig
    0.93
     wenigstens
    0.92
    ">!
    0.92
     shows
    0.91
    Activations Density 0.009%

    No Known Activations