© 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. 581
    Prev
    Next
    INDEX
    Explanations

    categories of items

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

    The neuron activates on isolated topic or category words (often abstract nouns) that label key themes or sections in the 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
     WITH
    0.45
     (:
    0.44
     (
    0.44
     (=
    0.43
     (?)
    0.43
     ("
    0.39
     footsteps
    0.39
     ((
    0.38
     ()
    0.37
     restores
    0.37
    POSITIVE LOGITS
    และความ
    0.53
    方面的
    0.53
     questões
    0.50
    ográficas
    0.46
    Issues
    0.46
    ajuan
    0.46
    挸
    0.46
    因素
    0.45
     이슈
    0.45
    aspetto
    0.45
    Activations Density 0.000%

    No Known Activations