© 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. 22-GEMMASCOPE-RES-131K
    7. 65367
    Prev
    Next
    INDEX
    Explanations

    programming keywords and list operations

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

    This neuron fires on code tokens that name commands or function calls (imperative operation identifiers 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_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
    ↵↵
    -1.34
    不清楚
    -1.23
    只是一
    -1.23
     their
    -1.20
    A
    -1.17
    づけ
    -1.10
    ’
    -1.09
    “
    -1.06
    −/−
    -1.06
    )
    -1.05
    POSITIVE LOGITS
    تفسير
    1.38
    鶿
    1.32
    معرفی
    1.23
    Jawab
    1.23
    ஊ
    1.22
    Appender
    1.22
    cenie
    1.19
    Enumerated
    1.18
     comerci
    1.18
    これも
    1.17
    Activations Density 0.013%

    No Known Activations