© 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. 29-GEMMASCOPE-2-RES-65K
    7. 1972
    Prev
    Next
    INDEX
    Explanations

    palaeolithic

    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_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <eos>
    0.66
     co
    0.61
    ‌
    0.60
     Spawn
    0.60
     तारीख
    0.59
     Plush
    0.59
     Knight
    0.57
     en
    0.57
    GPT
    0.57
     Baca
    0.57
    POSITIVE LOGITS
    Ре
    0.84
     meny
    0.81
     jambes
    0.78
    Х
    0.77
    ルの
    0.77
    从小
    0.77
     теркәлүсез
    0.77
     svoju
    0.76
    樎
    0.76
    čili
    0.75
    Activations Density 0.001%

    No Known Activations