© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8428
    Prev
    Next
    INDEX
    Explanations

    special characters or lists

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

    The neuron strongly activates on uncommon, low‐frequency tokens—i.e. those rare or “surprising” words or symbols 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_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
    ри
    0.85
    де
    0.73
    ви
    0.69
    م
    0.69
     (
    0.67
    Nueva
    0.65
    дава
    0.64
    м
    0.64
    Cancellation
    0.64
    με
    0.61
    POSITIVE LOGITS
     coisa
    0.93
     aproveitar
    0.91
     incrível
    0.89
     respostas
    0.88
     capazes
    0.86
     helpen
    0.84
     infringe
    0.84
     Beasley
    0.83
     ajud
    0.82
     каждым
    0.82
    Activations Density 0.001%

    No Known Activations