© 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. 7620
    Prev
    Next
    INDEX
    Explanations

    UTF-

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

    The neuron fires on the token “UTF,” i.e. references to UTF character‐encoding declarations.

    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
    ıc
    0.64
    ឈ
    0.59
    clickView
    0.58
     verbess
    0.56
     vittoria
    0.56
     तकनी
    0.55
     закончи
    0.55
     vencedor
    0.55
    क्य
    0.55
     הר
    0.54
    POSITIVE LOGITS
     toothpaste
    0.61
    bedrooms
    0.58
     Rayleigh
    0.55
    inare
    0.55
    oraj
    0.54
    ✄
    0.53
     residential
    0.53
    പോ
    0.53
     full
    0.52
     mortgage
    0.52
    Activations Density 0.000%

    No Known Activations