© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4426
    Prev
    Next
    INDEX
    Explanations

    Constants, enum, constants

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

    This neuron activates on uppercase constant or macro names (often in SNAKE_CASE) and related punctuation in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     त्यांच्या
    0.67
     soooo
    0.63
     दमखम
    0.63
    onaise
    0.61
    нении
    0.61
    ṑ
    0.61
    lägt
    0.60
     készült
    0.59
    ऱ
    0.59
     или
    0.59
    POSITIVE LOGITS
     DEFAULT
    0.90
    Enum
    0.86
    DEFAULT
    0.84
    Constants
    0.82
     enum
    0.79
     nameof
    0.79
     Constants
    0.76
    MessageType
    0.76
     NAME
    0.71
    常量
    0.70
    Activations Density 0.006%

    No Known Activations