© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10571
    Prev
    Next
    INDEX
    Explanations

    platform name

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

    This neuron fires most strongly on the final content word immediately before a sentence or segment boundary.

    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
     fiscales
    0.78
    a
    0.76
    บ
    0.73
    ла
    0.73
    الان
    0.68
     convuls
    0.68
    ब
    0.68
    ad
    0.66
     refinance
    0.65
    вила
    0.64
    POSITIVE LOGITS
    ữu
    0.89
     ассорти
    0.88
     Juice
    0.86
     деятельности
    0.83
     ရှိ
    0.82
    гация
    0.82
    ého
    0.82
     Wagen
    0.81
     деятельность
    0.80
     asalamualaikum
    0.79
    Activations Density 0.000%

    No Known Activations