© 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. 2370
    Prev
    Next
    INDEX
    Explanations

    Oh, followed by interjection or punctuation

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

    This neuron fires on utterance-initial interjections or discourse markers (e.g. “Oh,” “Yes,” “Yeah,” “All right,” etc.).

    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
    0.68
     reconstituted
    0.55
     profusely
    0.54
     (
    0.53
     necessities
    0.53
     provision
    0.53
     anv
    0.53
     entourage
    0.53
    িকে
    0.52
     exploits
    0.52
    POSITIVE LOGITS
    لی
    0.95
    ahaha
    0.88
     Побе
    0.88
    আচ্ছা
    0.84
     Gonna
    0.82
    اني
    0.82
     เหรอ
    0.82
    𝗷
    0.82
     โอ้
    0.81
    yeah
    0.80
    Activations Density 0.028%

    No Known Activations