© 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. 34-GEMMASCOPE-RES-131K
    7. 57117
    Prev
    Next
    INDEX
    Explanations

    posting and web editing issues

    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_34/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
    ダウンロード
    -1.13
     começaram
    -1.02
    BUT
    -1.02
    CMake
    -1.01
    我们
    -0.97
    velocityX
    -0.96
     vélos
    -0.96
    kommer
    -0.96
    θούν
    -0.92
    MAY
    -0.90
    POSITIVE LOGITS
     formatting
    1.45
     editing
    1.14
     edit
    1.14
     html
    1.05
     error
    1.05
     reply
    1.05
    うまく
    1.04
     upload
    1.03
     browser
    1.00
     HTML
    1.00
    Activations Density 0.062%

    No Known Activations