© 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. 34-GEMMASCOPE-RES-131K
    7. 106563
    Prev
    Next
    INDEX
    Explanations

    scan, scanning, scanned

    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_34/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
    dz
    -0.84
     PhpStorm
    -0.83
     CURLOPT
    -0.80
    atoto
    -0.77
     查询
    -0.77
     lòng
    -0.76
     tendencies
    -0.75
    احبه
    -0.75
     Sherry
    -0.73
     maiores
    -0.73
    POSITIVE LOGITS
     scan
    1.61
    扫描
    1.59
    scan
    1.45
    Scan
    1.43
     Scan
    1.39
     scanning
    1.37
     package
    1.36
    Scanning
    1.36
     scanned
    1.25
     Scanning
    1.23
    Activations Density 0.021%

    No Known Activations