© 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. 109011
    Prev
    Next
    INDEX
    Explanations

    page context or questions

    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
    终极
    -0.79
     bas
    -0.76
     wildest
    -0.71
     Weiterbildung
    -0.71
     malfunction
    -0.71
    接觸
    -0.69
     Gauss
    -0.68
     Argentino
    -0.68
    reiras
    -0.68
    الف
    -0.67
    POSITIVE LOGITS
     pageContext
    0.91
     européens
    0.88
    Out
    0.88
     PGC
    0.85
     CONS
    0.84
    PageContext
    0.84
    out
    0.80
    Dropout
    0.79
    setTime
    0.78
     Yakima
    0.77
    Activations Density 0.006%

    No Known Activations