© 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. 34-GEMMASCOPE-RES-131K
    7. 62561
    Prev
    Next
    INDEX
    Explanations

    specials and modifiers

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

    This neuron detects runs of indentation whitespace (i.e. tokens consisting of leading spaces used to indent 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    vien
    -0.97
     mexicanos
    -0.94
    GetHashCode
    -0.91
    adpleegd
    -0.89
     tuong
    -0.86
    EqualsAnd
    -0.86
    骉
    -0.83
    LER
    -0.81
     temporaire
    -0.81
     Saskatchewan
    -0.80
    POSITIVE LOGITS
     and
    0.96
     different
    0.84
    SqlDataReader
    0.82
    setOrder
    0.81
     mainly
    0.78
     Un
    0.77
    شتر
    0.77
     describes
    0.76
    Geografi
    0.75
    alipay
    0.75
    Activations Density 0.006%

    No Known Activations