© 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. 22-GEMMASCOPE-2-RES-65K
    7. 8621
    Prev
    Next
    INDEX
    Explanations

    file path separators

    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_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     functors
    0.61
     dead
    0.57
    নাম
    0.56
     reality
    0.56
     AO
    0.56
     bán
    0.55
    屌
    0.55
     officinalis
    0.55
     quận
    0.55
     PFAS
    0.55
    POSITIVE LOGITS
    abody
    0.88
     moyens
    0.84
    ီး
    0.84
    ferencia
    0.82
     flera
    0.82
    Several
    0.81
    rds
    0.80
    nce
    0.80
    း
    0.78
    engono
    0.78
    Activations Density 0.001%

    No Known Activations