© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119992
    Prev
    Next
    INDEX
    Explanations

    parsing files

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

    the word "parse" or its variations (parsing, parses) in technical or programming contexts.

    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
    ’
    -2.28
    t
    -1.82
     They
    -1.80
     If
    -1.79
    .
    -1.73
    d
    -1.73
     Which
    -1.70
     dengan
    -1.67
     ſever
    -1.64
    indest
    -1.59
    POSITIVE LOGITS
    茘
    1.95
    dersfield
    1.89
    ."
    1.83
    idjan
    1.79
    毎回
    1.76
     amenaz
    1.75
     dlatego
    1.75
    ⢫
    1.71
     oferty
    1.71
    ܜ
    1.68
    Activations Density 0.023%

    No Known Activations