© 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. 2123
    Prev
    Next
    INDEX
    Explanations

    of

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

    This neuron responds to motivational call-to-action phrases—especially imperative sentence openers like “To …” or “You ….”

    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
    ographic
    0.52
    вЂ
    0.52
    /
    0.47
    ०
    0.47
    of
    0.47
     並
    0.46
    //
    0.46
     ou
    0.46
     noticeable
    0.46
     bibliographic
    0.46
    POSITIVE LOGITS
     famiglie
    0.65
     insanların
    0.64
     pasukan
    0.63
     oamenii
    0.62
     guerras
    0.60
     soldats
    0.59
     hermano
    0.59
     মানুষকে
    0.58
     montañas
    0.57
     oameni
    0.57
    Activations Density 0.276%

    No Known Activations