© 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. 10-GEMMASCOPE-RES-131K
    7. 15105
    Prev
    Next
    INDEX
    Explanations

    code structures and arrays

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

    The neuron fires on occurrences of array‐type notations (e.g. “number[]”, “int[]”, and similar bracketed type declarations) in code and comments.

    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
     espri
    -1.35
    delijk
    -1.23
    LOGY
    -1.23
    鹮
    -1.23
    nost
    -1.23
    ISHED
    -1.18
     ?</
    -1.18
    CodeGen
    -1.17
    dimensional
    -1.13
    [&
    -1.13
    POSITIVE LOGITS
     your
    1.26
     naturais
    1.13
     deliciosos
    1.12
     חיצוני
    1.10
    你喜欢
    1.10
     this
    1.09
    kuat
    1.07
     each
    1.07
    jbl
    1.07
    </strong>
    1.06
    Activations Density 0.164%

    No Known Activations