© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12654
    Prev
    Next
    INDEX
    Explanations

    document separators

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

    The neuron specializes in spotting document structural markers—particularly volume/issue/part headings and their associated numbers separated by slashes or pipes.

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

    No Comments

    Negative Logits
    がなく
    -1.16
    が無い
    -1.14
     terrorismo
    -1.13
     puramente
    -1.12
     bagaimana
    -1.06
     включает
    -1.06
     folgenden
    -1.05
     erstmal
    -0.98
    他有
    -0.98
    ↵
    -0.97
    POSITIVE LOGITS
    Ji
    1.02
     egna
    0.97
    ANCH
    0.95
    pgsql
    0.91
    HILL
    0.91
    我的
    0.91
    numel
    0.90
     tiré
    0.89
    Te
    0.88
    ₚ
    0.88
    Activations Density 0.023%

    No Known Activations