© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91423
    Prev
    Next
    INDEX
    Explanations

    while you're waiting

    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
    開始
    -1.05
     zač
    -1.02
    很久
    -0.95
    どうやら
    -0.95
    に関しては
    -0.92
    食べた
    -0.91
    ctif
    -0.89
    جد
    -0.88
    ticum
    -0.87
    もあって
    -0.86
    POSITIVE LOGITS
     still
    1.61
     waiting
    1.48
     berlangsung
    1.44
     wait
    1.37
     await
    1.35
    still
    1.22
     waits
    1.21
    await
    1.20
     masih
    1.17
     ещё
    1.17
    Activations Density 0.031%

    No Known Activations