© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10929
    Prev
    Next
    INDEX
    Explanations

    empty string or null

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

    The neuron fires on numeric literal tokens (integers or decimals) in code or text.

    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
    CONST
    0.62
    ){
    0.57
    การ
    0.57
    appendText
    0.55
    Const
    0.53
    Highlight
    0.53
    Fix
    0.52
    Closing
    0.52
    COMP
    0.52
    EXT
    0.51
    POSITIVE LOGITS
     "";
    1.89
     "",
    1.84
     ""
    1.83
    ("")
    1.80
     '';
    1.80
     '',
    1.71
    ="";
    1.71
    ("");
    1.68
    ('')
    1.68
    =""
    1.60
    Activations Density 0.013%

    No Known Activations