© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 676
    Prev
    Next
    INDEX
    Explanations

    non- following a prefix

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

    The neuron activates on the “non” prefix (e.g. tokens in “non-uniform,” “non-Newtonian,” “non-structural,” etc.).

    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
    d
    0.91
    ર
    0.75
    son
    0.74
    하는
    0.74
    m
    0.73
    와
    0.73
    뭐
    0.73
    나
    0.73
    david
    0.72
    and
    0.72
    POSITIVE LOGITS
    țiile
    0.72
    γγελ
    0.64
     algorithmic
    0.63
     orthodontic
    0.62
    initpos
    0.62
    ţiile
    0.62
    operative
    0.61
     alignments
    0.61
    addAlignment
    0.61
    inputSelect
    0.60
    Activations Density 0.020%

    No Known Activations