© 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. 72149
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     data
    -1.10
    ּוֹ
    -1.07
     if
    -1.07
    ᾽
    -1.05
     management
    -1.02
    鳕
    -1.01
     policies
    -1.00
     klat
    -0.99
     or
    -0.96
    lrrrr
    -0.95
    POSITIVE LOGITS
    我們
    1.16
    ῖς
    1.09
     články
    1.08
     damaligen
    1.06
     katholischen
    1.05
     Porque
    1.05
     מים
    1.03
     diesmal
    1.02
     römischen
    1.02
    Fonto
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.