© 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. 5617
    Prev
    Next
    INDEX
    Explanations

    'eq', 'tab', 'KEY', 'btn' followed by ':' or '_'

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

    The neuron fires on numeric literals (numbers, especially multi‐digit or floating‐point constants) 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_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
    䢌
    0.52
    平台上
    0.52
     plateforme
    0.50
    abhave
    0.48
     fühlen
    0.48
    绿色
    0.47
     période
    0.46
    स्वामी
    0.46
    िफाई
    0.46
    EFI
    0.45
    POSITIVE LOGITS
    _
    0.73
    :
    0.58
    ;
    0.55
     Z
    0.55
    1
    0.54
     W
    0.52
    CopyTo
    0.52
     World
    0.50
    =
    0.50
     для
    0.49
    Activations Density 0.000%

    No Known Activations