© 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. 38774
    Prev
    Next
    INDEX
    Explanations

    sum of parts

    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
     warum
    -1.38
    ficador
    -1.31
    ₦
    -1.25
    
    -1.23
    фар
    -1.21
     generell
    -1.21
     ‚
    -1.20
     других
    -1.20
    ctory
    -1.20
    𝗮
    -1.20
    POSITIVE LOGITS
     It
    1.52
     its
    1.45
     всіх
    1.33
    >
    1.31
    各样的
    1.27
    它的
    1.22
    創意
    1.18
    してみると
    1.17
    "$_
    1.16
     الجميع
    1.16
    Activations Density 0.024%

    No Known Activations