© 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. 8234
    Prev
    Next
    INDEX
    Explanations

    emojis and positive expressions

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

    The neuron is specialized to pick out emotive punctuation and symbols—such as colons in emoticons, emoji characters, and similar expressive punctuation sequences.

    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
     process
    0.64
     intervention
    0.61
     internal
    0.60
     sources
    0.59
    ;
    0.57
     Hab
    0.55
     shortcuts
    0.55
     distribution
    0.54
     Process
    0.54
     institution
    0.54
    POSITIVE LOGITS
    😀
    0.98
    😃
    0.93
    😁
    0.90
    😮
    0.89
    😲
    0.86
     emoticon
    0.83
    😚
    0.82
    😓
    0.82
    😄
    0.81
    emoji
    0.80
    Activations Density 0.063%

    No Known Activations