© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 1265
    Prev
    Next
    INDEX
    Explanations

    list items or bullet points

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

    The neuron is detecting the presence of non‐ASCII (multi‐byte UTF‐8) characters in the 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
    i
    0.73
    </
    0.68
    &#
    0.68
    <0x0D>
    0.65
    )
    0.65
    ↵
    0.64
    [/
    0.64
    s
    0.63
      
    0.63
    <0xE3>
    0.63
    POSITIVE LOGITS
    ॕ
    0.80
    idcoin
    0.75
     कोणी
    0.71
    ௐ
    0.69
     oiseaux
    0.68
     evidente
    0.68
     scegliere
    0.67
     atractivo
    0.67
    <unused70>
    0.66
     अभिने
    0.66
    Activations Density 0.010%

    No Known Activations