© 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. 68469
    Prev
    Next
    INDEX
    Explanations

    parenthesized codes

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

    The neuron detects numeric citations or section‐reference numbers (including decimals) in legal or regulatory text.

    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
     it
    -2.84
     not
    -2.38
     as
    -2.36
    ↵
    -2.30
     to
    -2.06
     sebuah
    -1.95
     in
    -1.91
     but
    -1.91
     by
    -1.87
     an
    -1.75
    POSITIVE LOGITS
    n
    1.99
    would
    1.98
    Beberapa
    1.87
    Sekarang
    1.79
     ujar
    1.77
    焢
    1.74
    Berdasarkan
    1.73
    Tetapi
    1.72
    might
    1.71
    Two
    1.68
    Activations Density 0.040%

    No Known Activations