© 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. 10562
    Prev
    Next
    INDEX
    Explanations

    gradually motion or culmination

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

    The neuron consistently fires on verbs and verb‐like forms that describe physical movements, directions, or mechanical actions.

    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
     I
    0.68
     hadde
    0.65
     갔
    0.64
     A
    0.63
    女
    0.62
     있으
    0.62
     ಹಾಗೂ
    0.62
    I
    0.62
    J
    0.62
     N
    0.61
    POSITIVE LOGITS
     gradually
    0.99
     progressivement
    0.90
     постепенно
    0.87
     Gradually
    0.79
    变得
    0.75
     dramatically
    0.75
     symbolically
    0.74
    變得
    0.73
     culminates
    0.72
     momentous
    0.71
    Activations Density 0.003%

    No Known Activations