© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9278
    Prev
    Next
    INDEX
    Explanations

    code syntax with file/data operations

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

    This neuron detects programming‐style parameter or constant declarations—specifically type names (like String or Integer), assignment operators (≔/=), and their literal values.

    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_31_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
    长度
    0.61
     길이가
    0.56
     সংখ্যক
    0.55
     length
    0.55
    ਥ
    0.55
     ${(
    0.54
    NSInteger
    0.53
     lunghezza
    0.52
     int
    0.52
     intArray
    0.52
    POSITIVE LOGITS
     str
    0.58
     "-"
    0.55
    /"+
    0.55
    deviceName
    0.55
     "/"
    0.54
     toString
    0.54
     σύ
    0.53
     \""
    0.53
     userName
    0.52
    තාව
    0.52
    Activations Density 0.002%

    No Known Activations