© 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. 34-GEMMASCOPE-RES-131K
    7. 117472
    Prev
    Next
    INDEX
    Explanations

    programming keywords and identifiers

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

    The neuron consistently lights up on content words—especially named identifiers and proper nouns (module/type names in code, class/property names, and real‐world names like countries or teams).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     também
    -1.05
     campuran
    -1.03
     frère
    -1.01
     [
    -0.99
     those
    -0.99
     Fácil
    -0.97
    Síguenos
    -0.95
     acús
    -0.93
     ceux
    -0.93
     tepung
    -0.93
    POSITIVE LOGITS
    inton
    1.11
     började
    1.06
    iology
    1.05
    `,
    1.02
     iniziato
    1.02
    😫
    1.01
    tă
    1.00
    🥴
    0.99
    }_{
    0.98
    oten
    0.98
    Activations Density 0.012%

    No Known Activations