© 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. 2911
    Prev
    Next
    INDEX
    Explanations

    and in multiple languages

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

    The neuron activates strongly on content-bearing words (nouns, verbs, adjectives) rather than on common function words.

    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
     ,
    0.74
    ,//
    0.59
    >,
    0.55
    >,</
    0.55
    {},
    0.55
    ?,
    0.54
    ^{*},
    0.54
     ၊
    0.54
    ,
    0.54
    2
    0.54
    POSITIVE LOGITS
    そして
    0.74
     そして
    0.66
     आणि
    0.65
     ۋە
    0.61
    瘩
    0.61
    私の
    0.60
    mergeddata
    0.60
    我的
    0.60
    蟀
    0.59
    昨
    0.59
    Activations Density 0.372%

    No Known Activations