© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10941
    Prev
    Next
    INDEX
    Explanations

    let's go

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

    The neuron fires on high‐impact promotional cues and calls to action—words and phrases used to urge or persuade the reader with urgency (e.g. “So,” “hurry,” “get,” “now,” “limited supply”).

    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
     learns
    0.61
     helpful
    0.54
    featureType
    0.50
     متخصص
    0.50
     παρά
    0.49
    .*\
    0.49
     بشكل
    0.49
    órc
    0.49
     mög
    0.49
     bribery
    0.48
    POSITIVE LOGITS
     Hurry
    0.96
     hurry
    0.85
    赶紧
    0.77
    urry
    0.69
     অতএব
    0.68
     seize
    0.68
     加入
    0.65
    UIS
    0.65
    ダウンロード
    0.65
    Grab
    0.64
    Activations Density 0.319%

    No Known Activations