© 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. 15829
    Prev
    Next
    INDEX
    Explanations

    technical concepts and requirements

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

    the presence of numeric expressions (digits and numbers) 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
    c
    0.71
     kvůli
    0.68
    t
    0.68
     after
    0.66
     après
    0.63
    e
    0.63
    f
    0.63
    ळ्यात
    0.63
    k
    0.61
     onSuccess
    0.60
    POSITIVE LOGITS
    及び
    0.82
    又は
    0.82
     enquiry
    0.75
     gruesome
    0.73
     डायरेक्टली
    0.73
     automó
    0.71
     comical
    0.71
    ाह
    0.71
     शौचालय
    0.70
     वहाँ
    0.70
    Activations Density 0.158%

    No Known Activations