© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68729
    Prev
    Next
    INDEX
    Explanations

    array declarations

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

    The neuron activates on the square‐bracket “[]” tokens that denote array types or array declarations in code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     respectively
    -1.47
     jezelf
    -1.45
    section
    -1.42
    ulite
    -1.41
     concernant
    -1.38
     བ
    -1.37
    fromUtf
    -1.36
    кг
    -1.35
     জন্য
    -1.35
     tableta
    -1.33
    POSITIVE LOGITS
    쫀
    1.61
     are
    1.56
    簠
    1.52
     the
    1.50
    Składniki
    1.43
     newfound
    1.42
     natür
    1.39
    </em>
    1.37
     feiner
    1.30
     your
    1.27
    Activations Density 0.002%

    No Known Activations