© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36182
    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
     While
    -1.07
     With
    -1.05
     while
    -1.02
    kish
    -1.01
    日起
    -1.00
     oorspron
    -0.99
     will
    -0.99
     Along
    -0.98
     usual
    -0.97
     groots
    -0.97
    POSITIVE LOGITS
    狁
    1.20
    somebody
    1.20
     bizi
    1.17
     новое
    1.15
    orious
    1.11
     dring
    1.10
     trés
    1.09
    ということ
    1.09
     ofte
    1.09
    猻
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.