© 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. 129238
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on programming identifiers—tokens used as variable, attribute, or parameter names in code snippets.

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

    keywords and technical terms

    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
    もありますが
    -1.06
     électro
    -1.05
    CLUYE
    -0.99
     cuivre
    -0.99
     falsi
    -0.99
    糧
    -0.98
    搅拌
    -0.98
     thép
    -0.98
     religieux
    -0.97
    ⻑
    -0.97
    POSITIVE LOGITS
     its
    1.21
     your
    1.12
     Persön
    1.02
    corrhi
    1.00
    の方に
    0.96
    posizioni
    0.96
     their
    0.96
    際には
    0.96
    Should
    0.93
    它
    0.93
    Activations Density 0.129%

    No Known Activations