© 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-262K
    7. 5836
    Prev
    Next
    INDEX
    Explanations

    javascript path module

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     usur
    0.93
     estiver
    0.78
     বুল
    0.76
     Niro
    0.76
     backing
    0.74
     launched
    0.74
     seigneur
    0.73
    哪個
    0.73
     bulge
    0.72
     ¬
    0.72
    POSITIVE LOGITS
    Webpack
    0.86
    Spice
    0.83
     ${({
    0.80
    Encript
    0.79
    StateMachine
    0.79
    吘
    0.78
    )}},
    0.76
     મોત
    0.75
    Tere
    0.74
    IPv
    0.74
    Activations Density 0.000%

    No Known Activations