© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9251
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

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

    The neuron flags code elements that declare or use concrete data types or literal values—e.g. type keywords (As Double, As Integer, As String, Date) and numeric constants.

    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
    etchup
    0.61
    decreasing
    0.57
    STERBEDATUM
    0.55
     धा
    0.54
    multiply
    0.54
    frameN
    0.54
    vVertex
    0.53
    蛏
    0.53
    ౪
    0.53
    và
    0.53
    POSITIVE LOGITS
     quatro
    0.60
     for
    0.56
     musically
    0.56
     outta
    0.56
     out
    0.55
     zon
    0.55
     zoning
    0.54
     MEET
    0.54
     Particular
    0.53
     seis
    0.53
    Activations Density 0.000%

    No Known Activations