© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30222
    Prev
    Next
    INDEX
    Explanations

    wait, no, what?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    さぁ
    -0.88
    是吗
    -0.80
     heuristic
    -0.80
     منم
    -0.75
     ось
    -0.71
    Took
    -0.71
    %>
    -0.71
    是啊
    -0.71
    ញ
    -0.71
     bå
    -0.69
    POSITIVE LOGITS
     wait
    6.31
    Wait
    5.03
    wait
    5.03
     Wait
    4.84
    WAIT
    3.98
     WAIT
    3.94
     waits
    3.50
     waited
    3.11
     espera
    2.69
     await
    2.59
    Activations Density 0.031%

    No Known Activations