© 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. 9084
    Prev
    Next
    INDEX
    Explanations

    salutations and matters

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

    the neuron activates on numeric tokens and quantitative figures in the text.

    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
     incluyendo
    0.92
     اغلب
    0.91
     MgII
    0.84
    ۓ
    0.81
     чтоб
    0.81
     உன்
    0.80
     icin
    0.80
     کنه
    0.80
     अक्सर
    0.79
     বেশী
    0.79
    POSITIVE LOGITS
     آقای
    0.84
     gentlemen
    0.80
    Quite
    0.77
    Implementation
    0.77
    That
    0.77
    Mr
    0.76
    I
    0.76
    Paragraph
    0.74
    ET
    0.74
    IP
    0.73
    Activations Density 0.027%

    No Known Activations