© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8858
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the key trigger and action words (e.g. “When,” “Target,” “Destroy,” “Send”) that begin or drive effect/instruction clauses in rule‐ or card‐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
    <unused532>
    0.87
     કરવું
    0.84
     Acqu
    0.84
     kilobytes
    0.83
     pédicule
    0.82
     অনেকের
    0.81
    zovaniyu
    0.80
     caractéristique
    0.79
     recuerdo
    0.79
     carbides
    0.78
    POSITIVE LOGITS
    ug
    0.90
    в
    0.84
    ip
    0.76
     visiting
    0.75
    /
    0.74
    wn
    0.72
    way
    0.71
    ar
    0.70
    -
    0.70
    у
    0.70
    Activations Density 0.001%

    No Known Activations