© 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. 10439
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    This neuron fires on open‐class “content” words (nouns, verbs, adjectives) rather than on 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
    n
    0.78
     nought
    0.76
    斯的
    0.71
    nings
    0.69
    nate
    0.68
    ným
    0.66
     ポケット
    0.64
    ・
    0.64
    玤
    0.64
    ০
    0.63
    POSITIVE LOGITS
    wort
    0.82
    easy
    0.78
     locaux
    0.78
    ehr
    0.78
    一定的
    0.76
    epoch
    0.75
     Sorg
    0.74
     लीजिएगा
    0.73
    ർട്ട
    0.73
    exact
    0.71
    Activations Density 0.000%

    No Known Activations