© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4263
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, hundred

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

    hundred and large numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    ৩
    0.77
    ১
    0.60
     ৩
    0.57
    ৪
    0.54
    ২
    0.52
     ২
    0.48
     ১
    0.44
    六年
    0.43
    五年
    0.41
    三年
    0.40
    POSITIVE LOGITS
     hundred
    1.41
    hundred
    1.23
     Hundred
    1.20
     hundert
    1.14
    Hundred
    1.11
     trăm
    1.11
    oo
    1.10
    ۰۰
    1.03
    百
    1.03
     सय
    1.01
    Activations Density 0.583%

    No Known Activations