© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59717
    Prev
    Next
    INDEX
    Explanations

    cvs/CMSSW

    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
     Nineteen
    -0.71
     Dustin
    -0.71
     in
    -0.67
     Jeanne
    -0.67
     Jed
    -0.66
    Pietro
    -0.63
    {(
    -0.63
    parentNode
    -0.63
    if
    -0.62
    nestjs
    -0.61
    POSITIVE LOGITS
    ា
    0.78
    🤿
    0.74
     adatto
    0.73
     silverware
    0.71
    IBLES
    0.71
     Kalifor
    0.70
    ⠢
    0.69
    Oro
    0.68
    Ƴ
    0.68
     이동
    0.68
    Activations Density 0.496%

    No Known Activations