© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57997
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    This neuron detects numeric tokens, including standalone numbers and numbers embedded in identifiers.

    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
    atized
    -1.86
    豋
    -1.80
    (!__
    -1.77
     They
    -1.76
    他们
    -1.71
    unno
    -1.70
    asties
    -1.68
     escuro
    -1.67
    苼
    -1.67
    Problemas
    -1.65
    POSITIVE LOGITS
     of
    3.34
     to
    2.72
     its
    2.20
     such
    2.11
     will
    2.11
     each
    1.73
     into
    1.70
     with
    1.66
     in
    1.63
     where
    1.60
    Activations Density 0.021%

    No Known Activations