© 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. 5986
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
     Only
    0.52
     Bodies
    0.48
     detract
    0.46
    䡆
    0.45
    ექტ
    0.44
     Advancement
    0.43
    ತ್ರೆ
    0.43
     Adding
    0.42
    ável
    0.42
     Output
    0.42
    POSITIVE LOGITS
     dozen
    0.50
     दर्जन
    0.48
     হাজারের
    0.47
    または
    0.45
    dozen
    0.45
    ‑
    0.44
    Ir
    0.44
    th
    0.44
     হয়েছিলেন
    0.44
     hari
    0.42
    Activations Density 0.242%

    No Known Activations