© 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. 825
    Prev
    Next
    INDEX
    Explanations

    measuring units and quantities

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

    numerical ranges and measurements

    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
     پیسے
    0.30
     پیسہ
    0.29
     സംവിധ
    0.28
     বহুদিন
    0.28
     evidencias
    0.27
    Ⅰ
    0.27
     tetahi
    0.27
     সম্বন্ধে
    0.27
    िफिकेट
    0.27
    Percentages
    0.26
    POSITIVE LOGITS
     minimum
    0.71
     ish
    0.67
    minimum
    0.66
    +,
    0.64
    +.
    0.64
     maximum
    0.63
    +/-
    0.63
     worth
    0.61
     apiece
    0.61
     total
    0.59
    Activations Density 0.762%

    No Known Activations