© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10347
    Prev
    Next
    INDEX
    Explanations

    fill standards

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

    The neuron chiefly lights up on longer, multisyllabic content words (i.e. complex vocabulary rather than short 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_31_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
     BLUEN
    0.55
    atum
    0.54
     Sted
    0.53
     Blazers
    0.52
     Gdy
    0.51
     BIL
    0.51
     amal
    0.50
    沓
    0.50
     dolgo
    0.50
     solns
    0.49
    POSITIVE LOGITS
     multid
    0.59
    бавить
    0.55
     ermöglichen
    0.54
    Ƒ
    0.52
    élix
    0.51
    haust
    0.51
    ronom
    0.50
     समायोजित
    0.50
     चीजों
    0.50
    ющей
    0.50
    Activations Density 0.121%

    No Known Activations