© 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. 22-GEMMASCOPE-RES-131K
    7. 69269
    Prev
    Next
    INDEX
    Explanations

    variable declarations and data structures

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

    This neuron detects programming code syntax (e.g., variable assignments, array literals, arrow functions) rather than natural-language text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     on
    -1.30
     when
    -1.24
     during
    -1.07
     at
    -1.05
     JUST
    -1.04
     koš
    -1.02
     ALWAYS
    -1.01
    鏄
    -1.00
     or
    -0.99
     comes
    -0.98
    POSITIVE LOGITS
     diejenigen
    1.11
    resulting
    1.09
    ִּ
    1.05
     각
    1.05
     каждого
    1.05
     ameste
    1.05
    <thead>
    1.03
    转换成
    1.03
     насеље
    1.02
     individus
    1.01
    Activations Density 0.025%

    No Known Activations