© 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. 11160
    Prev
    Next
    INDEX
    Explanations

    heuristic, listen, Episode

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

    The neuron responds most strongly to low‐frequency or uncommon tokens 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
    ح
    0.83
    তার
    0.75
     touted
    0.73
    ermek
    0.73
    ف
    0.72
     aches
    0.70
     viola
    0.70
     Niko
    0.69
     lecturing
    0.69
    俟
    0.68
    POSITIVE LOGITS
     desember
    0.85
    er
    0.84
    wounded
    0.80
     другие
    0.77
    processable
    0.77
    profiss
    0.75
     согласо
    0.75
    operation
    0.74
    spirit
    0.73
     концов
    0.73
    Activations Density 0.000%

    No Known Activations