© 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. 129363
    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
     ostensibly
    -1.01
     imb
    -1.01
     non
    -0.99
    JHEP
    -0.96
     closet
    -0.94
    蜗
    -0.93
     recent
    -0.93
    窗外
    -0.91
     рем
    -0.91
     door
    -0.89
    POSITIVE LOGITS
    难得
    1.06
    满是
    1.01
     barnet
    1.00
     donat
    0.98
    Specifik
    0.98
    還要
    0.96
    还可以
    0.95
     triko
    0.93
     masjid
    0.93
     waarschijnlijk
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.