© 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. 10-GEMMASCOPE-RES-131K
    7. 84004
    Prev
    Next
    INDEX
    Explanations

    system calls, abbreviations, technical identifiers

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

    This neuron consistently fires on the exact token “SC” (often as part of C constant or macro names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -3.98
    ?”
    -2.89
    ”—
    -2.72
    ࿙
    -2.61
    鯷
    -2.55
     That
    -2.45
    什么
    -2.42
     Each
    -2.42
    arbonato
    -2.38
    縂
    -2.38
    POSITIVE LOGITS
    u
    2.88
    SC
    2.63
    不时
    2.45
    </strong>
    2.44
     gleiche
    2.41
     нескольких
    2.39
    ii
    2.38
    ies
    2.31
    or
    2.30
    ↵
    2.28
    Activations Density 0.011%

    No Known Activations