© 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. 38493
    Prev
    Next
    INDEX
    Explanations

    programming props

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

    The neuron strongly responds to standalone numeric literals (e.g. version numbers, prop‐counts, IDs) in the 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
    ."
    -2.56
    ка
    -2.48
    )=\
    -2.39
    of
    -2.36
    (
    -2.30
    穢
    -2.30
    ט
    -2.28
     This
    -2.25
    }
    -2.23
    {\
    -2.22
    POSITIVE LOGITS
    たまに
    2.91
     ofere
    2.78
    を選び
    2.75
    樒
    2.72
    𖣘
    2.63
    ﮦ
    2.61
     lunares
    2.58
     beginnen
    2.55
    のおすすめ
    2.50
    寕
    2.50
    Activations Density 0.002%

    No Known Activations