© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2900
    Prev
    Next
    INDEX
    Explanations

    wood and materials

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

    easy, practical, resistant

    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
     ხელისუფლების
    0.61
    批判
    0.60
     ხელისუფ
    0.60
    当局
    0.57
     政府
    0.56
     道
    0.55
    知り
    0.54
     いう
    0.53
    議論
    0.53
    事情
    0.52
    POSITIVE LOGITS
     inox
    1.02
     Ø
    0.92
     robuste
    0.86
     robust
    0.84
     anthracite
    0.83
     ø
    0.82
     hochwert
    0.80
     ajustable
    0.79
     ergonom
    0.79
     AISI
    0.79
    Activations Density 0.133%

    No Known Activations