© 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. 9093
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by unusual punctuation or formatting characters (e.g. typographic quotation marks and non-standard whitespace tokens).

    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
    ار
    0.76
    ený
    0.68
    şı
    0.66
    ä
    0.65
    dı
    0.64
    oglu
    0.64
    ↵↵
    0.64
    op
    0.63
    ور
    0.63
    oč
    0.63
    POSITIVE LOGITS
    などは
    0.83
     znalaz
    0.82
    なども
    0.79
     rattled
    0.78
     reliant
    0.77
     prácticamente
    0.76
    など
    0.75
     inklusive
    0.75
     accompanies
    0.74
     might
    0.74
    Activations Density 0.001%

    No Known Activations