© 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. 12384
    Prev
    Next
    INDEX
    Explanations

    speak flexibility

    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
     шта
    1.34
     oameni
    1.32
    er
    1.31
    
    1.30
    ্ভব
    1.28
     fino
    1.27
    норий
    1.21
     atores
    1.20
    ногие
    1.18
    yek
    1.18
    POSITIVE LOGITS
     minced
    1.47
     overeen
    1.38
     antimicrobial
    1.37
    نا
    1.36
    ি
    1.35
    ه
    1.34
    ా
    1.33
     enclosed
    1.32
    ください
    1.30
     accordance
    1.29
    Activations Density 0.000%

    No Known Activations