© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6424
    Prev
    Next
    INDEX
    Explanations

    physical units and rates

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

    units of physical quantities

    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
    玧
    0.46
     Фила
    0.44
    应该
    0.44
    參数
    0.42
    蛐
    0.42
     Override
    0.41
     పరి
    0.41
    GTBase
    0.41
    تحانات
    0.41
    ",[],"
    0.40
    POSITIVE LOGITS
    ⋅
    0.79
    ·
    0.78
    ∙
    0.74
    
    0.73
     kg
    0.66
     cm
    0.65
    kg
    0.64
    ·
    0.63
    sec
    0.62
    •
    0.60
    Activations Density 0.023%

    No Known Activations