© 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. 11022
    Prev
    Next
    INDEX
    Explanations

    and so

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

    This neuron responds to the first substantive word at the start of a new paragraph or section.

    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
    l
    0.85
    uje
    0.82
     vortices
    0.81
     hostilities
    0.80
     zeolite
    0.80
    जिये
    0.79
     mileage
    0.79
     mejora
    0.78
     coincided
    0.78
     campuses
    0.77
    POSITIVE LOGITS
    ي
    0.86
     CONTRIBUT
    0.79
    ি
    0.77
     eigentlich
    0.76
    其實
    0.75
    actually
    0.73
     BEEN
    0.73
     CLIENTI
    0.72
     Actually
    0.71
     CHRISTIAN
    0.71
    Activations Density 0.000%

    No Known Activations