© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    very + adjective

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

    The neuron fires on words used as degree modifiers or intensifiers (e.g. long, much, quite, great, very).

    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
    jenigen
    0.51
    :_
    0.50
    iou
    0.49
     grossesse
    0.48
    oze
    0.47
    </code>
    0.47
     sufficiently
    0.47
     लिए
    0.46
    ಂಧ
    0.46
    o
    0.46
    POSITIVE LOGITS
    ‌ترین
    0.56
     utilização
    0.53
    リア
    0.52
    ﺮ
    0.52
    早已
    0.52
     swath
    0.52
    ﺪ
    0.52
     sämt
    0.51
    функциона
    0.51
    可选
    0.51
    Activations Density 0.000%

    No Known Activations