© 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. 7881
    Prev
    Next
    INDEX
    Explanations

    Mayo Clinic female reproductive

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

    The neuron strongly activates on long, content-heavy words (especially uncommon product- or marketing-style nouns/adjectives) rather than on common short 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
    t
    0.85
    id
    0.85
    r
    0.81
    ných
    0.79
    ana
    0.76
    u
    0.76
    トート
    0.74
    tart
    0.73
    ae
    0.73
    dU
    0.73
    POSITIVE LOGITS
     съм
    0.85
    ко
    0.82
    Зна
    0.82
    ва
    0.81
    к
    0.79
    Ꮐ
    0.79
    িনীত
    0.78
    Основ
    0.77
    лиз
    0.77
    ючись
    0.76
    Activations Density 0.001%

    No Known Activations