© 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. 10954
    Prev
    Next
    INDEX
    Explanations

    XML structure and multilingual content

    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
    Not in Any Lists

    No Comments

    Negative Logits
     years
    0.90
    years
    0.88
    dır
    0.81
     tek
    0.81
    ians
    0.80
    but
    0.79
    යි
    0.79
     n
    0.78
    aol
    0.78
     शक्त
    0.77
    POSITIVE LOGITS
    cC
    0.96
    Πα
    0.96
    رشف
    0.92
    లిన
    0.90
    ጠቀ
    0.90
    きて
    0.87
    scrollView
    0.87
     شریف
    0.86
     Vettel
    0.86
    ূপে
    0.86
    Activations Density 0.000%

    No Known Activations