© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22584
    Prev
    Next
    INDEX
    Explanations

    file paths and technical directories

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

    The neuron fires on forward-slash characters ("/") used as delimiters (e.g. in file paths, URLs, or version strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    .
    -1.71
    There
    -1.57
     Those
    -1.53
    Those
    -1.51
     ocorrer
    -1.48
     prêmio
    -1.48
     utilizó
    -1.48
    ichtete
    -1.47
     &
    -1.42
    Some
    -1.42
    POSITIVE LOGITS
    OUTUBE
    1.64
    ᐠ
    1.55
    ́i
    1.55
    囖
    1.50
     harness
    1.50
    岁月
    1.48
    tiert
    1.45
     /
    1.41
     بام
    1.41
    lblNewLabel
    1.41
    Activations Density 0.066%

    No Known Activations