© 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. 130224
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently lights up on programming identifiers (e.g. function names, method or variable names) in source code.

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

    code generated by

    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
     their
    -1.23
    |
    -1.07
     (
    -1.02
     would
    -1.02
    _
    -1.01
     for
    -0.98
     many
    -0.98
     with
    -0.97
     dengan
    -0.95
    _{
    -0.94
    POSITIVE LOGITS
     réserver
    1.11
    拍了拍
    1.06
     iniciar
    1.02
    尪
    1.01
    влению
    1.01
    Jaunes
    0.99
    摇了
    0.98
     resultant
    0.98
     osserva
    0.97
     ejecuta
    0.97
    Activations Density 0.001%

    No Known Activations