© 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. 15761
    Prev
    Next
    INDEX
    Explanations

    Russian words (`веще`, `ство`)

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

    The neuron sharply activates on longer, low‐frequency content words (including multi‐syllabic terms and uncommon tokens) across languages.

    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
    thren
    0.85
    тике
    0.82
    Nuevo
    0.77
    LAMP
    0.77
    turno
    0.77
    ър
    0.76
     humano
    0.73
     umano
    0.73
    ەڵ
    0.71
    쐞
    0.70
    POSITIVE LOGITS
     notebooks
    0.82
    {
    0.80
     ਦ
    0.77
    詳細は
    0.75
     weep
    0.73
     banks
    0.72
    erry
    0.72
     సె
    0.72
    猷
    0.71
    க்கப்பட்டது
    0.70
    Activations Density 0.000%

    No Known Activations