© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130444
    Prev
    Next
    INDEX
    Explanations

    The neuron detects definition‐site identifiers in code—i.e. names of classes, structs, interfaces, forms, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code structure and class names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    dlc
    -1.01
     Além
    -1.01
     Parece
    -1.00
     reembols
    -1.00
    brian
    -0.99
    cdi
    -0.96
    ᅟ
    -0.96
    Cdt
    -0.96
     também
    -0.94
     Popis
    -0.94
    POSITIVE LOGITS
    One
    1.13
    Very
    1.10
    M
    1.08
     gave
    0.96
    B
    0.95
    Other
    0.95
     very
    0.95
     didn
    0.94
    0
    0.93
    </strong>
    0.92
    Activations Density 0.000%

    No Known Activations