© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73589
    Prev
    Next
    INDEX
    Explanations

    filtering logic in code

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

    This neuron is keyed to code delimiters—especially semicolons that mark the ends of statements.

    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
    タス
    -0.88
    Votre
    -0.71
    ścia
    -0.69
     unusually
    -0.68
     sonst
    -0.68
    墊
    -0.68
    ચ
    -0.68
    下げ
    -0.68
    々と
    -0.67
     Entomology
    -0.67
    POSITIVE LOGITS
     Filter
    1.54
    Filter
    1.41
     filter
    1.30
    FILTER
    1.27
    setFilter
    1.19
     FILTER
    1.16
    filter
    1.04
     filters
    0.95
     Filters
    0.93
     filtra
    0.90
    Activations Density 0.026%

    No Known Activations