© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10240
    Prev
    Next
    INDEX
    Explanations

    insurance, technology, or classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    能力的
    1.30
    ونس
    1.22
    uders
    1.20
     REPORTS
    1.17
     elevations
    1.13
    ckel
    1.11
     diff
    1.10
     ais
    1.09
    ክ
    1.09
     Herzeg
    1.09
    POSITIVE LOGITS
    іл
    1.14
     понятие
    1.11
    գ
    1.07
    дцать
    1.06
     цена
    1.05
    ใจ
    1.05
    ারা
    1.05
    
    1.03
    ⚫
    1.03
    ourism
    1.01
    Activations Density 0.009%

    No Known Activations