© 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. 654
    Prev
    Next
    INDEX
    Explanations

    introducing examples or lists

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

    The neuron selectively activates on question constructions—especially question‐mark punctuation.

    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
     然而
    0.79
     تمامی
    0.76
     這
    0.75
     🙌
    0.74
     però
    0.73
     grazie
    0.73
     虽然
    0.73
     selepas
    0.70
     dernière
    0.69
     sassy
    0.69
    POSITIVE LOGITS
    ?”
    1.05
    ?"
    0.96
    ?)
    0.95
    ？
    0.93
    ؟.
    0.92
    ？」
    0.88
    ?
    0.84
    ?\
    0.84
    ?.
    0.79
    ؟
    0.79
    Activations Density 0.063%

    No Known Activations