© 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. 5598
    Prev
    Next
    INDEX
    Explanations

    This neuron detects technical, procedural action verbs used in instructional contexts (e.g., “points,” “works,” “change,” “clean”).

    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
     Figs
    0.66
     또는
    0.65
    または
    0.65
     photographs
    0.64
     greatly
    0.64
     doubtless
    0.64
     Decorative
    0.62
    ,
    0.62
     Visualization
    0.59
     conceivably
    0.59
    POSITIVE LOGITS
    立马
    0.63
     ибо
    0.61
     ঘৃ
    0.59
     swoim
    0.59
    farmers
    0.59
    резать
    0.58
     contrairement
    0.58
    воен
    0.57
    whitelist
    0.57
    macht
    0.56
    Activations Density 0.859%

    No Known Activations