© 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. 22-GEMMASCOPE-RES-131K
    7. 36462
    Prev
    Next
    INDEX
    Explanations

    public static final enum const extern

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

    This neuron detects programming‐language syntax tokens, especially code keywords (like public, static, final) and related punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     with
    -1.39
     partially
    -1.36
     just
    -1.18
     usually
    -1.18
     will
    -1.13
     by
    -1.13
     provide
    -1.13
     results
    -1.12
     taking
    -1.12
     two
    -1.11
    POSITIVE LOGITS
     acqua
    1.19
     reconocidos
    1.16
     vijf
    1.14
    ఝ
    1.12
     saine
    1.11
     visiteurs
    1.09
     deaktiviert
    1.08
     eenig
    1.06
    laren
    1.05
     spectateurs
    1.05
    Activations Density 0.021%

    No Known Activations