© 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. 71428
    Prev
    Next
    INDEX
    Explanations

    future plans

    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
    </i>
    -1.61
    onyms
    -1.43
     your
    -1.41
    цыі
    -1.37
    0
    -1.35
    ΕΛ
    -1.34
     svého
    -1.33
    lojik
    -1.29
    8
    -1.27
     dezen
    -1.24
    POSITIVE LOGITS
     on
    1.42
     about
    1.37
     ways
    1.24
     теперь
    1.22
    Deaf
    1.20
    itoba
    1.17
    intera
    1.16
     behövs
    1.16
     try
    1.15
    はどう
    1.15
    Activations Density 0.020%

    No Known Activations