© 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. 58150
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases

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

    The neuron detects long runs of the same character (i.e. tokens made up of repeated single characters).

    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
     and
    -1.91
    libat
    -1.58
    ikti
    -1.58
    刹那
    -1.56
     Rumuni
    -1.55
    聍
    -1.53
     well
    -1.46
    contoh
    -1.45
     to
    -1.45
     very
    -1.43
    POSITIVE LOGITS
    '
    1.97
    新しい
    1.77
    ’
    1.77
    .
    1.66
    她
    1.61
    4
    1.59
     увели
    1.56
     Maintenant
    1.52
     Ajoutez
    1.48
     Choisissez
    1.46
    Activations Density 0.001%

    No Known Activations