© 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. 4828
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on standalone instructional or informational headings—especially “what is…” or “what causes…” questions and step-by-step product/instruction titles.

    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
     των
    0.81
    д
    0.73
    offsetHeight
    0.73
    ochemistry
    0.72
    Η
    0.70
     สา
    0.70
    啊
    0.69
    О
    0.66
    眸
    0.66
    从
    0.66
    POSITIVE LOGITS
     Christian
    0.75
     Marlon
    0.75
     Disney
    0.74
     Adolf
    0.74
     Dorothy
    0.74
     César
    0.74
     Dolores
    0.74
     Bigfoot
    0.73
     Baptist
    0.73
     Woolf
    0.73
    Activations Density 0.001%

    No Known Activations