© 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. 22-GEMMASCOPE-RES-131K
    7. 32795
    Prev
    Next
    INDEX
    Explanations

    foreign technical terms

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

    This neuron activates on programming-related identifiers and file‐name tokens (e.g. CamelCase names and “.h” includes) in code snippets.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     its
    -1.13
    อย่างไร
    -1.11
    のお知らせ
    -1.09
    latimes
    -1.09
    Significado
    -1.08
     The
    -1.06
    tvguide
    -1.06
    何故
    -1.03
    気がします
    -1.03
    FAQs
    -1.02
    POSITIVE LOGITS
     dals
    1.23
     magnifique
    1.22
     ۱۸
    1.20
     leone
    1.20
     congrès
    1.20
     vinci
    1.16
    <bos>
    1.15
     condol
    1.14
     Pesca
    1.14
     interi
    1.13
    Activations Density 0.022%

    No Known Activations