© 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. 8202
    Prev
    Next
    INDEX
    Explanations

    ?

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

    The neuron activates on interrogative contexts—that is, question words and sentences posing questions.

    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
     👌
    0.75
    あらゆる
    0.73
     birçok
    0.71
     👍
    0.68
     molte
    0.68
     vilket
    0.66
    无比
    0.65
     completo
    0.64
     mnog
    0.63
     allerlei
    0.63
    POSITIVE LOGITS
    ?
    3.03
    ？
    2.92
    ؟
    2.70
    ?\
    2.66
    ?</
    2.58
    ?"
    2.56
    ?}
    2.55
    ?<
    2.50
    ?",
    2.45
    ?)
    2.44
    Activations Density 1.324%

    No Known Activations