© 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. 110984
    Prev
    Next
    INDEX
    Explanations

    README _

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

    The neuron fires on ALL-CAP identifiers containing underscores (e.g. WEBPACK_BUILD, LAYOUT_INFLATER, rules_go).

    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
     ‘
    -2.30
    0
    -2.25
    '
    -2.11
    In
    -2.09
     should
    -1.93
    ‘
    -1.93
    (
    -1.91
    ↵
    -1.91
    ”,
    -1.91
    A
    -1.85
    POSITIVE LOGITS
    聍
    2.30
    ſtra
    2.00
    镡
    1.94
     rése
    1.89
    柺
    1.88
     efek
    1.85
     moletom
    1.84
    卺
    1.80
     mû
    1.78
    嵛
    1.77
    Activations Density 0.002%

    No Known Activations