© 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. 8210
    Prev
    Next
    INDEX
    Explanations

    dysphoria or metastasis

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

    The neuron fires on numeric category codes (decimal numbers) that appear after backslashes in classification paths.

    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
    abele
    0.86
     inteligentes
    0.86
    <<(
    0.84
    дравствуйте
    0.82
    ваты
    0.82
     consect
    0.81
     yukarı
    0.81
    ([^
    0.80
    лару
    0.80
    梫
    0.80
    POSITIVE LOGITS
    I
    0.93
    This
    0.91
    You
    0.79
    أ
    0.78
    There
    0.77
    She
    0.77
    It
    0.75
    Cette
    0.72
     ノー
    0.71
    An
    0.71
    Activations Density 0.001%

    No Known Activations