© 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. 10-GEMMASCOPE-RES-131K
    7. 7285
    Prev
    Next
    INDEX
    Explanations

    Flint, McNabb, ADS, Hills

    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_10/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
    ي
    -2.91
     &
    -2.61
    轳
    -2.47
    ですので
    -2.44
    s
    -2.41
    ،
    -2.39
    튿
    -2.39
    1
    -2.33
     they
    -2.30
    ですから
    -2.30
    POSITIVE LOGITS
     It
    2.48
     tenets
    2.33
    轫
    2.27
    癆
    2.17
     упаковка
    2.16
     potrzeb
    1.99
     участке
    1.93
    ↵↵
    1.91
     tangible
    1.90
     transformar
    1.90
    Activations Density 0.003%

    No Known Activations