© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    dull ache

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

    The neuron responds to complex, formal academic or scientific vocabulary—especially longer, Latinate or technical terms.

    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
     Etat
    0.66
     chemokine
    0.63
     illusion
    0.61
     Antarctic
    0.61
     cactus
    0.60
     psychedelic
    0.60
     ૧
    0.60
     fetches
    0.59
     midnight
    0.59
     indignation
    0.59
    POSITIVE LOGITS
    Otros
    0.64
    ⅾ
    0.64
    <unused292>
    0.62
    ূলক
    0.60
    <unused361>
    0.60
    䏲
    0.59
    㣙
    0.58
    <unused731>
    0.58
    otros
    0.57
     మరియు
    0.57
    Activations Density 0.671%

    No Known Activations