© 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. 8578
    Prev
    Next
    INDEX
    Explanations

    the [concept] introduced

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ي
    0.80
    acie
    0.78
    buat
    0.78
     ле
    0.74
     العمل
    0.74
    增强
    0.74
     ações
    0.74
    似乎
    0.74
     ه
    0.74
    主要是
    0.73
    POSITIVE LOGITS
     Challenge
    0.95
     Difference
    0.91
     History
    0.89
     Problem
    0.82
     Way
    0.81
     story
    0.81
     Story
    0.80
     difference
    0.79
     Dile
    0.78
     Importance
    0.78
    Activations Density 0.004%

    No Known Activations