© 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. 98642
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

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

    The neuron specializes in spotting the volume number (the numeric “11” style token) in formal legal or journal citations.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Its
    -2.55
    Their
    -2.48
     geringen
    -2.47
     üblichen
    -2.45
    ukone
    -2.42
    嚳
    -2.38
    You
    -2.34
    They
    -2.31
    Your
    -2.28
     sicheren
    -2.28
    POSITIVE LOGITS
    ene
    2.97
    n
    2.64
    h
    2.58
    ra
    2.55
    le
    2.45
    ),
    2.39
    )/
    2.38
    I
    2.30
    c
    2.30
    ars
    2.28
    Activations Density 0.094%

    No Known Activations