© 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. 22041
    Prev
    Next
    INDEX
    Explanations

    country

    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
     this
    -1.67
     with
    -1.63
     a
    -1.50
     in
    -1.45
     while
    -1.44
     such
    -1.35
    僦
    -1.35
     for
    -1.35
     the
    -1.34
    コミュニ
    -1.33
    POSITIVE LOGITS
    “
    1.67
    жа
    1.56
     них
    1.48
     térmica
    1.48
     Thessal
    1.48
    liwości
    1.46
    私の
    1.39
    
    1.39
    任何
    1.39
     educativas
    1.38
    Activations Density 0.021%

    No Known Activations