© 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. 38387
    Prev
    Next
    INDEX
    Explanations

    is followed by a word

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

    The neuron is detecting occurrences of the token “is” (in any case or as part of identifiers) in code.

    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
     of
    -2.66
     and
    -2.64
    t
    -2.19
    emia
    -2.17
     are
    -2.11
     after
    -2.03
    to
    -1.98
    a
    -1.98
    },
    -1.93
    .”
    -1.93
    POSITIVE LOGITS
     adesivo
    1.97
    <bos>
    1.92
    
    1.90
    doesn
    1.74
    batal
    1.73
     legais
    1.73
    乆
    1.70
    真剣
    1.70
     estampada
    1.69
     Selecting
    1.69
    Activations Density 0.006%

    No Known Activations