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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39211
    Prev
    Next
    INDEX
    Explanations

    verifying node, role, or arguments

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

    This neuron detects occurrences of the term “check” (e.g. in function or variable names) in code.

    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
     "
    -2.63
     we
    -2.41
     idyllic
    -2.39
    ’
    -2.38
     instill
    -2.34
     dunklen
    -2.34
     Gründung
    -2.33
    木の
    -2.31
    v
    -2.30
     $\
    -2.28
    POSITIVE LOGITS
     itſelf
    3.27
    注意事
    3.03
    鄖
    3.00
    鄠
    3.00
     fatis
    3.00
    扨
    2.97
    哢
    2.92
    踅
    2.91
     fevere
    2.86
     моя
    2.84
    Activations Density 0.031%

    No Known Activations