© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15892
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on action‐command words—i.e. imperative verbs that appear in instructions or how-to steps.

    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_31_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
     Celebration
    0.56
    okit
    0.56
     polymerase
    0.56
     syrup
    0.55
     decking
    0.55
    uming
    0.54
    嫨
    0.54
     Syrup
    0.54
     harina
    0.53
    뷸
    0.53
    POSITIVE LOGITS
    Optional
    0.63
    Tools
    0.60
     Tools
    0.57
    optional
    0.56
    ちょ
    0.56
     Optional
    0.55
    Configurations
    0.54
    attrib
    0.53
    Conditional
    0.53
    conditional
    0.53
    Activations Density 0.002%

    No Known Activations