© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11207
    Prev
    Next
    INDEX
    Explanations

    separators and defining abstract concepts

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

    The neuron strongly activates on numeric tokens with decimal points (floating‐point numbers).

    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
     мі
    0.98
     му
    0.95
     д
    0.86
     м
    0.85
     дет
    0.85
     най
    0.83
     ста
    0.82
     па
    0.79
     яке
    0.79
     т
    0.78
    POSITIVE LOGITS
     checkboxes
    0.86
    で作
    0.83
    alen
    0.81
    alım
    0.81
    leme
    0.80
    meli
    0.80
     loosen
    0.80
    SOLE
    0.79
    MES
    0.79
    lös
    0.79
    Activations Density 0.000%

    No Known Activations