© 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. 39836
    Prev
    Next
    INDEX
    Explanations

    describes how to do something

    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
     in
    -2.73
     there
    -2.42
     it
    -1.85
     then
    -1.84
     by
    -1.67
        
    -1.51
     to
    -1.50
     on
    -1.38
     as
    -1.37
     have
    -1.27
    POSITIVE LOGITS
     how
    1.84
    Примеча
    1.49
    بهترین
    1.45
    امکان
    1.45
     dommage
    1.45
    نحوه
    1.43
    تصویر
    1.38
    بیش
    1.38
    گوشی
    1.38
     désol
    1.35
    Activations Density 0.089%

    No Known Activations