© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15890
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and fractions

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

    The neuron activates on numeric tokens with decimal points (i.e. 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_31_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
    Macrophages
    0.56
     به‌
    0.55
    ’.
    0.54
    ‌,
    0.52
     म्ह
    0.52
     pabbaj
    0.51
    ’-
    0.50
     Massimo
    0.50
    マックス
    0.50
    ക്ക്‌
    0.50
    POSITIVE LOGITS
     கட
    0.61
     outlook
    0.59
     $|\
    0.59
    турой
    0.57
     "|"
    0.57
     ""
    0.56
    ፐ
    0.56
    ''
    0.55
    腕
    0.55
     Capit
    0.55
    Activations Density 0.149%

    No Known Activations