© 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. 7683
    Prev
    Next
    INDEX
    Explanations

    explaining complex topics

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

    The neuron flags semantically “content” words (especially nouns and other key information–carrying terms) and ignores common function words.

    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
     ライト
    0.83
     に
    0.79
     ま
    0.78
     الى
    0.77
     フォ
    0.77
     から
    0.76
     inwards
    0.75
     内
    0.73
     більш
    0.73
    ⵥ
    0.72
    POSITIVE LOGITS
     nations
    0.81
     watersheds
    0.77
     federally
    0.76
    దం
    0.75
     envisions
    0.75
     nonprofits
    0.70
     nedenle
    0.70
    했고
    0.69
     countries
    0.69
     roadway
    0.69
    Activations Density 0.480%

    No Known Activations