© 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. 13237
    Prev
    Next
    INDEX
    Explanations

    saying "also" or "likewise"

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

    This neuron fires on exclamatory expressions of excitement or congratulations (e.g. “new,” “follower,” “congrats,” “fun,” “great show!”)

    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
     빠르게
    0.49
    ัญลักษณ์
    0.48
    Instagram
    0.47
     밝혔다
    0.46
    ამაშ
    0.46
    <unused338>
    0.45
    <unused2206>
    0.45
    <unused314>
    0.44
    เหล่านี้
    0.43
     الترك
    0.43
    POSITIVE LOGITS
     tambien
    0.67
    къ
    0.63
     ايضا
    0.61
     recollection
    0.60
     т
    0.59
     bzw
    0.59
     то
    0.57
     nao
    0.57
     '
    0.55
     stalwart
    0.55
    Activations Density 0.448%

    No Known Activations