© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11836
    Prev
    Next
    INDEX
    Explanations

    could be

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

    The neuron fires on words that express possibility or uncertainty—that is, modal auxiliaries and hedge terms like may, might/could, possible, etc.

    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
     なかっ
    1.20
    қ
    1.20
    Ｎ
    1.15
     poter
    1.09
    Ｏ
    1.07
     keď
    1.05
    ी
    1.02
    𝗴
    1.00
    𝗦
    1.00
    𝗡
    1.00
    POSITIVE LOGITS
    س
    1.52
     conceivably
    1.41
    ารย์
    1.30
     Possibly
    1.16
     possibly
    1.12
    ა
    1.09
    possibly
    1.07
    tom
    1.05
    ن
    1.05
    گزاری
    1.03
    Activations Density 0.561%

    No Known Activations