© 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. 5978
    Prev
    Next
    INDEX
    Explanations

    Anything multilingual

    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
     start
    0.74
    只
    0.67
    коль
    0.67
    жив
    0.67
    starttime
    0.67
    elle
    0.65
     মুজিব
    0.65
    >);
    0.65
     Jews
    0.65
     lunga
    0.64
    POSITIVE LOGITS
     Anything
    0.87
     לק
    0.87
    Anything
    0.85
     बेटर
    0.81
     педаго
    0.80
     게
    0.78
    một
    0.77
     किसी
    0.76
     ANYTHING
    0.76
    ្រ
    0.76
    Activations Density 0.000%

    No Known Activations