© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8956
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    The neuron fires on subjective, sentiment‐laden words or phrases (e.g. “excited,” “finicky,” “happier,” “interesting”) that express personal opinions or reactions.

    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
    доста
    0.59
     happenings
    0.57
     galerinha
    0.56
    𝗙
    0.55
     тебя
    0.54
     MyDB
    0.54
    idać
    0.54
     நீங்கள்
    0.54
    出来ます
    0.53
     fantastical
    0.53
    POSITIVE LOGITS
    .
    0.64
    ®.
    0.56
    *.
    0.56
    .*
    0.54
    .<
    0.54
    .{
    0.54
     whose
    0.53
     ofthe
    0.52
    .\
    0.51
    .(
    0.50
    Activations Density 0.544%

    No Known Activations