© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8358
    Prev
    Next
    INDEX
    Explanations

    engaging everyone, appealing to

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

    The neuron strongly fires on common adverbs (e.g. simply, actually, never) that intensify or qualify statements.

    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
     Chiara
    1.03
     Jeju
    1.02
     Marbella
    0.99
     Puebla
    0.98
     Salamanca
    0.98
    Provence
    0.97
    뀨
    0.95
    Skew
    0.94
    Bingo
    0.94
     Shibuya
    0.94
    POSITIVE LOGITS
    в
    0.71
     clicking
    0.70
    imer
    0.67
    uer
    0.67
    гене
    0.65
     rapidly
    0.64
    們
    0.64
    ină
    0.61
    omer
    0.61
    ل
    0.61
    Activations Density 0.002%

    No Known Activations