© 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. 11581
    Prev
    Next
    INDEX
    Explanations

    exclamations followed by jokes or lighthearted phrases

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

    The neuron is detecting ASCII‐style emoticons (e.g. “:)”, “:D”, “;)”, “🙂”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    emoticons and emoji-like punctuation sequences.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    casual, expressive internet-chat markers—emotive punctuation, laughter/interjections, emoticons, and forum/IRC-style conventions indicating an informal, enthusiastic tone.

    oai_token-act-pair · gpt-5Triggered 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
     bilateral
    0.66
     diy
    0.61
     bersifat
    0.61
     juncture
    0.61
     capsules
    0.58
     fréquente
    0.58
     area
    0.58
     segments
    0.57
     inti
    0.57
     букмекерлер
    0.57
    POSITIVE LOGITS
    haha
    1.13
    Haha
    1.10
    hehe
    1.05
     ;)
    1.02
     😉
    1.01
     =)
    1.01
    哈哈哈
    1.00
    Honestly
    0.98
    😜
    0.97
    yeah
    0.97
    Activations Density 0.025%

    No Known Activations