© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15316
    Prev
    Next
    INDEX
    Explanations

    precedent limit management idea imitate

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

    The neuron fires strongly on tokens ending in “or.”

    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
    or
    0.81
    س
    0.72
    스의
    0.69
     Banc
    0.68
    H
    0.68
    इस
    0.68
    物に
    0.67
    物的
    0.67
    orium
    0.66
     главное
    0.66
    POSITIVE LOGITS
     गेंदबाजों
    0.83
     éléments
    0.78
     raisons
    0.77
     changements
    0.77
     thèse
    0.76
    férences
    0.75
     facteurs
    0.74
     exigences
    0.73
     streamers
    0.73
     біль
    0.73
    Activations Density 0.000%

    No Known Activations