© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7194
    Prev
    Next
    INDEX
    Explanations

    facial expressions and body language

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

    The neuron is strongly activated by pronouns, character names, and reporting‐speech verbs in dialogue attribution (i.e. the “speaker tags” and related action words that accompany lines of dialogue).

    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_31_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
     feel
    0.60
     inwest
    0.56
    feel
    0.55
    "<<
    0.55
    を感じ
    0.53
    从业
    0.53
     obses
    0.52
     feels
    0.52
     सुनते
    0.52
     metast
    0.52
    POSITIVE LOGITS
     smirk
    1.35
     smiles
    1.16
    笑
    1.14
     smiled
    1.13
     laughs
    1.09
     wink
    1.09
     smile
    1.08
     cười
    1.08
     chuckled
    1.05
     grinned
    1.05
    Activations Density 0.213%

    No Known Activations