© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    other people or opponents

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     разработан
    1.09
     ২০২০
    1.03
     ২৬
    1.01
     భాగంగా
    1.00
    6
    0.99
     бы
    0.99
    setBorder
    0.96
     outperform
    0.95
    2
    0.95
    8
    0.94
    POSITIVE LOGITS
     seus
    1.24
     mensen
    1.22
     descricao
    1.13
     ellos
    1.12
     الاخر
    1.12
     strangers
    1.12
     stranger
    1.08
     lidí
    1.08
     människ
    1.07
    |.|.|
    1.07
    Activations Density 0.931%

    No Known Activations