© 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. 12867
    Prev
    Next
    INDEX
    Explanations

    explain why / how

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

    The neuron fires strongly on tokens that appear as the very first word of a new text segment or block.

    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
     강화
    0.72
    왕
    0.72
    他們
    0.70
     Rider
    0.70
     vue
    0.70
     personne
    0.70
     salles
    0.70
    급
    0.70
    認為
    0.70
    ại
    0.69
    POSITIVE LOGITS
     nanofibers
    0.86
    стная
    0.86
     Beyoncé
    0.84
    า
    0.84
     Protección
    0.84
     retinol
    0.84
    ных
    0.82
     cosmetology
    0.82
    стные
    0.80
    lma
    0.80
    Activations Density 0.000%

    No Known Activations