© 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. 29-GEMMASCOPE-2-RES-65K
    7. 1890
    Prev
    Next
    INDEX
    Explanations

    else keywords

    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_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    십니까
    0.69
    zig
    0.66
     KC
    0.66
    borist
    0.65
     legitim
    0.65
    /"><
    0.63
     येलो
    0.62
     AKA
    0.62
     madad
    0.61
    ющее
    0.60
    POSITIVE LOGITS
     else
    1.02
    else
    0.95
    Else
    0.85
    球
    0.73
    ↵
    0.68
    ELSE
    0.67
    सार
    0.65
    ↵↵
    0.64
     را
    0.64
     Стаўкі
    0.64
    Activations Density 0.322%

    No Known Activations