© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5928
    Prev
    Next
    INDEX
    Explanations

    now, followed by punctuation

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

    The neuron fires on the discourse-transition word “Now” when it starts a sentence to signal a shift or new segment in the text.

    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
     আজও
    0.82
    ным
    0.76
     zatím
    0.74
     still
    0.73
    y
    0.71
     umbrellas
    0.69
     descent
    0.68
     yada
    0.68
    ي
    0.67
     आजही
    0.66
    POSITIVE LOGITS
    adays
    1.19
    ruz
    1.05
    oczes
    0.98
    væ
    0.98
    days
    0.87
    varande
    0.87
    mehr
    0.85
    arranty
    0.82
    heres
    0.81
    껏
    0.78
    Activations Density 0.141%

    No Known Activations