© 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. 2879
    Prev
    Next
    INDEX
    Explanations

    reading or writing books

    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
    
    2.83
    cit
    2.77
    cose
    2.72
    kiego
    2.70
    c
    2.68
     béton
    2.56
    cier
    2.53
     setback
    2.52
    getParent
    2.52
    𝗽
    2.50
    POSITIVE LOGITS
    べき
    2.80
    Ра
    2.70
    worms
    2.65
     able
    2.64
    きた
    2.62
    能
    2.62
    quela
    2.57
    ка
    2.57
    های
    2.54
    ত্বের
    2.53
    Activations Density 0.061%

    No Known Activations