© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128535
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on module path segments in Dart/Flutter import statements (e.g. the “package:” or “dart:” parts of import lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Code imports and technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ویتامین
    -1.34
    aringan
    -1.19
    ﷲ
    -1.13
    ׇ
    -1.12
    Tá
    -1.11
    ₁)
    -1.09
    ')}}">
    -1.07
     Pfar
    -1.07
    ἵ
    -1.07
    ……」
    -1.05
    POSITIVE LOGITS
     such
    1.12
    に向けて
    1.02
     esfuerzan
    0.98
     една
    0.96
     considérée
    0.94
    jshint
    0.93
    だけではなく
    0.93
    えない
    0.92
    も見
    0.92
    っていない
    0.91
    Activations Density 0.001%

    No Known Activations