© 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. 8529
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that are floating‐point numbers (decimal numeric values).

    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
     Mein
    0.77
    m
    0.75
    aunque
    0.75
    eous
    0.74
     atheist
    0.74
    l
    0.74
    eo
    0.73
    即便
    0.73
    et
    0.73
    рые
    0.73
    POSITIVE LOGITS
    .’”
    0.77
    আগ
    0.75
    Το
    0.75
    चलिए
    0.74
     તો
    0.74
    ToUpper
    0.74
     สำหรับ
    0.73
     liné
    0.72
     ผ้า
    0.72
    Გ
    0.72
    Activations Density 0.000%

    No Known Activations