© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15611
    Prev
    Next
    INDEX
    Explanations

    numbers and categories

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

    The neuron strongly activates on numeric tokens containing 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
    ки
    0.72
    Լ
    0.72
    Fonts
    0.70
    وط
    0.70
    ك
    0.68
    حات
    0.67
    ផ្ល
    0.66
    ून
    0.66
     blossoms
    0.65
     Ори
    0.64
    POSITIVE LOGITS
     pero
    1.01
     sedangkan
    0.92
    แต่
    0.92
    だけでなく
    0.91
    뿐
    0.91
    pedido
    0.90
     berita
    0.88
     memperoleh
    0.87
     borrar
    0.87
     reuni
    0.86
    Activations Density 0.000%

    No Known Activations