© 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. 30246
    Prev
    Next
    INDEX
    Explanations

    Spark, Partitioning, equivalence, Sunday

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

    The neuron specifically lights up on programming‐style tokens—API calls, language keywords, method names, and configuration identifiers (e.g. Spark, JDBC, read, option, StructType, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    を感じ
    -0.71
     Bik
    -0.69
     syllables
    -0.69
    Fq
    -0.69
     waf
    -0.68
    nicks
    -0.66
    あく
    -0.66
    FixedSize
    -0.66
    ftw
    -0.65
     tủ
    -0.65
    POSITIVE LOGITS
    anson
    0.88
    häuser
    0.81
     Ansari
    0.77
     alış
    0.77
     ente
    0.77
    urnum
    0.76
     lick
    0.75
    ppchen
    0.75
     Cumming
    0.75
    FICHA
    0.74
    Activations Density 0.013%

    No Known Activations