© 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. 22-GEMMASCOPE-RES-131K
    7. 73052
    Prev
    Next
    INDEX
    Explanations

    code structures or file paths

    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_22/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
     depuis
    -1.13
     in
    -1.13
    Should
    -1.02
    hever
    -1.00
    سية
    -0.99
    Since
    -0.96
    ندم
    -0.95
     chwil
    -0.94
    !».
    -0.92
     konden
    -0.91
    POSITIVE LOGITS
    齣
    0.92
     Unilever
    0.91
     reclining
    0.90
     BOTH
    0.90
     advoc
    0.88
    xaml
    0.86
    ängen
    0.85
     Deut
    0.85
    書いた
    0.85
     MNC
    0.85
    Activations Density 0.000%

    No Known Activations