© 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. 5149
    Prev
    Next
    INDEX
    Explanations

    names or titles after commas

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

    This neuron fires on standalone discourse markers and interjections—single-word exclamations or address phrases (e.g. “Gracious!”, “No, no!”, “Why,” “Yes or no, please”) that punctuate or steer the flow of conversation.

    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
      
    0.89
    ,
    0.74
    (
    0.73
     (
    0.68
    /
    0.67
    .
    0.66
    -
    0.65
    y
    0.63
     -
    0.61
     servitude
    0.61
    POSITIVE LOGITS
     えっ
    0.94
     הם
    0.86
     těch
    0.86
     সেই
    0.85
    那個
    0.83
     पुल्लिंग
    0.82
    那位
    0.81
     இந்தப்
    0.79
     protože
    0.79
     Балт
    0.79
    Activations Density 0.138%

    No Known Activations