© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15393
    Prev
    Next
    INDEX
    Explanations

    Mathematical constants

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

    The neuron fires strongly on the very first word token that starts a fresh paragraph.

    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
     Charg
    0.73
     algebraica
    0.68
     cnpj
    0.64
     Borden
    0.64
     Jacks
    0.64
     ~\
    0.64
     subscripts
    0.64
    불어
    0.64
     সঞ্জীবনী
    0.63
     ---------------
    0.63
    POSITIVE LOGITS
    uticas
    0.80
    河
    0.77
    歐洲
    0.76
    ЕЛ
    0.75
    хии
    0.75
     spying
    0.74
    фри
    0.74
     bleak
    0.74
     Европы
    0.73
     reservation
    0.72
    Activations Density 0.000%

    No Known Activations