© 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. 22-GEMMASCOPE-RES-131K
    7. 25017
    Prev
    Next
    INDEX
    Explanations

    numbers, lines, Q:

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

    The main thing this neuron does is find standalone numeric references (e.g., line or page numbers) in formal/legal texts.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     recensioni
    -1.16
     varje
    -0.98
    REVIEW
    -0.95
    Andere
    -0.93
    ducers
    -0.92
     morire
    -0.92
    给我们
    -0.91
    其中
    -0.91
     auteurs
    -0.90
    向着
    -0.90
    POSITIVE LOGITS
     after
    1.15
    ῖς
    0.99
    ("")]
    0.98
     GoogleFonts
    0.98
     adjacent
    0.97
     hjemmeside
    0.96
     approximately
    0.94
     mochilas
    0.91
     Quantification
    0.91
     confirmado
    0.90
    Activations Density 0.004%

    No Known Activations