© 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. 47189
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms

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

    The neuron strongly activates on scientific paper titles or section headings—particularly lines of capitalized technical phrases often followed by a colon.

    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
     hygienic
    -0.77
     extruded
    -0.75
    preprocess
    -0.75
    ĝis
    -0.73
     fondness
    -0.73
    SGS
    -0.72
     throbbing
    -0.71
    比较好
    -0.70
     Bellini
    -0.70
     Stress
    -0.69
    POSITIVE LOGITS
     mechanism
    1.14
     reaction
    1.07
     reactions
    0.99
     mechanisms
    0.97
     channels
    0.97
     channel
    0.95
     Channel
    0.93
     Reaction
    0.91
    Channel
    0.91
     barrier
    0.88
    Activations Density 0.077%

    No Known Activations