© 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-262K
    7. 145568
    Prev
    Next
    INDEX
    Explanations

    for building or ://www

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Sketches
    0.74
    创
    0.74
     Wall
    0.69
    GCG
    0.67
     Revised
    0.67
    bill
    0.66
     olay
    0.65
     والله
    0.65
    Wall
    0.65
    रिपोर्ट
    0.64
    POSITIVE LOGITS
    πον
    0.73
    PAS
    0.68
    ⇜
    0.67
     पार
    0.66
    ప్ప
    0.66
    ption
    0.66
    ደር
    0.65
    পুরে
    0.65
    釀
    0.65
    പ്പാ
    0.64
    Activations Density 0.003%

    No Known Activations