© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47957
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    This neuron activates on code identifiers (variable, function, and type names) rather than keywords or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     επίσης
    -1.38
    правки
    -1.35
     ακόμα
    -1.33
    Either
    -1.32
    летний
    -1.31
     ακό
    -1.29
    xnn
    -1.29
    corbic
    -1.27
    遵循
    -1.23
    ]-\
    -1.23
    POSITIVE LOGITS
     because
    1.68
     Because
    1.53
     they
    1.45
    因為
    1.43
     it
    1.40
     about
    1.38
     riguard
    1.30
    を用
    1.27
     avven
    1.24
     dimost
    1.23
    Activations Density 0.021%

    No Known Activations