© 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-16K
    7. 3963
    Prev
    Next
    INDEX
    Explanations

    leave or departure

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ॉय
    0.62
    නම්
    0.61
    녕하세요
    0.58
    idler
    0.58
    gic
    0.56
     คว
    0.56
    ី
    0.56
    敉
    0.56
     Freedman
    0.55
    یکن
    0.55
    POSITIVE LOGITS
     leave
    5.61
     leaving
    5.49
     Leave
    5.37
    Leave
    5.27
    leave
    5.13
     Leaving
    5.02
    leaving
    4.88
    Leaving
    4.80
     leaves
    4.58
     Leaves
    4.02
    Activations Density 0.368%

    No Known Activations