© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107131
    Prev
    Next
    INDEX
    Explanations

    words starting with "Wa" or "Wau"

    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
    starting
    -1.00
     starting
    -0.90
     благода
    -0.88
    Starting
    -0.87
    remp
    -0.75
     Travels
    -0.75
    GYPT
    -0.71
    solids
    -0.71
     ام
    -0.71
    sium
    -0.70
    POSITIVE LOGITS
     Wa
    1.16
    Wa
    1.07
     wa
    1.04
    로그인
    0.80
    walla
    0.79
     Waz
    0.77
     Wai
    0.75
    放大
    0.74
    -¡
    0.74
     croit
    0.74
    Activations Density 0.023%

    No Known Activations