© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6666
    Prev
    Next
    INDEX
    Explanations

    Fair winds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     заместитель
    0.62
    Ab
    0.60
    欢
    0.60
    ள்ளன
    0.59
    exp
    0.57
    เดียวกัน
    0.56
    饑
    0.55
    oraj
    0.55
     objections
    0.54
    둥
    0.53
    POSITIVE LOGITS
    ground
    0.83
     debt
    0.76
     Dealing
    0.74
     Debt
    0.74
    ADY
    0.74
    mares
    0.73
     ชม
    0.71
    ICO
    0.69
    債
    0.69
    winds
    0.68
    Activations Density 0.067%

    No Known Activations