© 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. 7012
    Prev
    Next
    INDEX
    Explanations

    code constructs: function, array

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

    This neuron detects the opening brace of a JavaScript object literal (i.e. the “{” that begins an object returned by a function).

    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
    '
    -1.93
     you
    -1.65
    \
    -1.61
     &
    -1.49
     drei
    -1.47
    \_
    -1.44
     samoch
    -1.42
     męski
    -1.41
    ਫ਼
    -1.40
     trente
    -1.39
    POSITIVE LOGITS
    </strong>
    1.74
     With
    1.71
     That
    1.65
    SPORTS
    1.56
     some
    1.52
    </b>
    1.52
    はこんな感じ
    1.48
     similar
    1.43
     something
    1.41
     sedangkan
    1.41
    Activations Density 0.001%

    No Known Activations