© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    positive sentiment closers

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

    The neuron is triggered by polite, self‐referential or apologetic language—especially first‐person pronouns and words like “sorry,” “help,” “I,” “but,” and emphatic 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
     ،
    0.73
    ，
    0.72
    ?",
    0.67
    ?,
    0.64
    :'',
    0.64
    NAMEN
    0.63
     ,
    0.61
    это
    0.61
    ?',
    0.60
    ،
    0.60
    POSITIVE LOGITS
     🤗
    0.90
     🙂
    0.88
     😊
    0.87
     👍
    0.86
     :)
    0.84
     😉
    0.83
     💪
    0.79
     ;)
    0.78
     😎
    0.77
     👌
    0.74
    Activations Density 0.359%

    No Known Activations