© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9061
    Prev
    Next
    INDEX
    Explanations

    flash, lightning

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

    The neuron responds to occurrences of the token “Flash” (or “flash” as a standalone or in compound names).

    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
    marker
    0.63
    periods
    0.61
    variety
    0.61
    Variety
    0.60
    InfoWindow
    0.59
    tum
    0.59
    냔
    0.59
    Processor
    0.58
    Marker
    0.57
     Marker
    0.57
    POSITIVE LOGITS
     flash
    1.49
    flash
    1.35
     Flash
    1.30
    Flash
    1.27
     flashes
    1.24
    FLASH
    1.23
     flashed
    1.19
     FLASH
    1.13
    闪
    1.08
     bolt
    0.93
    Activations Density 0.059%

    No Known Activations