© 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-262K
    7. 12510
    Prev
    Next
    INDEX
    Explanations

    test-driven development

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ر
    1.66
     follows
    1.39
     humana
    1.33
    нні
    1.32
    م
    1.32
     Nós
    1.31
     वीं
    1.30
     loving
    1.26
     दीवाना
    1.24
    미
    1.24
    POSITIVE LOGITS
    𝙡
    1.77
    𝙙
    1.74
     umfang
    1.63
    ء
    1.59
    %@",
    1.57
    𝐃
    1.50
    gut
    1.46
    чити
    1.45
    extensive
    1.44
    setzungen
    1.39
    Activations Density 0.000%

    No Known Activations