© 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. 8285
    Prev
    Next
    INDEX
    Explanations

    print statement or function call

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

    The neuron fires on call-to-action and promotional language—phrases inviting the reader to follow/save/subscribe or get regular updates.

    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
    س
    0.74
    uaje
    0.71
     pove
    0.70
    sman
    0.68
    jasmine
    0.68
    Nueva
    0.68
    ubert
    0.66
    娯
    0.66
     fern
    0.65
    Kentucky
    0.65
    POSITIVE LOGITS
    [])
    0.83
     PSI
    0.78
    chis
    0.77
    テー
    0.76
    )’
    0.75
     sentidos
    0.75
    продук
    0.75
    ዶ
    0.75
    teries
    0.75
    IC
    0.75
    Activations Density 0.000%

    No Known Activations