© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2237
    Prev
    Next
    INDEX
    Explanations

    the color cyan

    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
    Not in Any Lists

    No Comments

    Negative Logits
     والط
    1.39
    🠀
    1.39
    णिज्य
    1.37
    
    1.33
    
    1.29
     casks
    1.26
    achio
    1.26
     применяется
    1.25
     amounted
    1.24
    stackrel
    1.23
    POSITIVE LOGITS
     kebakaran
    1.14
    glyphs
    1.09
     Dov
    1.09
     Уда
    1.07
     tentative
    1.06
    to
    1.03
    酢
    1.03
     ace
    1.03
    ాతం
    1.02
     Runnable
    1.01
    Activations Density 0.005%

    No Known Activations