© 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. 13357
    Prev
    Next
    INDEX
    Explanations

    This neuron detects HTML character-entity tokens (e.g. “ ” and similar numeric/hex escape sequences).

    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
    r
    1.21
    l
    1.13
     capillaries
    0.97
    lai
    0.95
    pong
    0.94
     orchids
    0.93
     clutches
    0.93
    lak
    0.93
    lardan
    0.91
    rung
    0.91
    POSITIVE LOGITS
    ं
    0.67
    Visibility
    0.66
    ophysical
    0.65
    Mystery
    0.65
     المط
    0.65
    店内
    0.65
     Анастасия
    0.64
    Description
    0.63
     Mystery
    0.62
    WindowTitle
    0.62
    Activations Density 0.002%

    No Known Activations