© 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. 10804
    Prev
    Next
    INDEX
    Explanations

    government websites

    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
    icide
    0.79
    änz
    0.77
    erebbe
    0.76
    ོན་
    0.76
    निया
    0.75
    ものは
    0.75
     进入
    0.74
     жили
    0.73
    ávají
    0.73
    ㅓ
    0.72
    POSITIVE LOGITS
    ghed
    0.78
     reda
    0.67
     کوم
    0.67
    断
    0.66
     blur
    0.65
     Revel
    0.65
     remove
    0.65
     Archive
    0.64
     pallets
    0.64
    δει
    0.63
    Activations Density 0.005%

    No Known Activations