© 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. 9585
    Prev
    Next
    INDEX
    Explanations

    conditional statements `[[` and `(... )`

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

    This neuron detects placeholder or “fill-in-the-blank” tokens (blanks, underscores, ellipses, X/Y/Z, and similar generic placeholders) indicating missing or variable content.

    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
    AAD
    0.72
    userID
    0.71
    LGBT
    0.65
    <?=$
    0.65
     অন্যদিকে
    0.62
    পরিচিত
    0.61
    ofthe
    0.61
    のかな
    0.61
    
    0.61
    ની
    0.61
    POSITIVE LOGITS
     REACTORS
    0.65
     memorandum
    0.63
     functionality
    0.63
     シューズ
    0.62
     Reactors
    0.61
     Rats
    0.61
     drainage
    0.59
     Sauce
    0.59
     Receiver
    0.58
     we
    0.57
    Activations Density 0.037%

    No Known Activations