© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27790
    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
     immediately
    -1.14
     or
    -1.14
     only
    -1.04
     bahaya
    -1.04
     their
    -1.04
     prevent
    -1.00
     dinas
    -0.99
     like
    -0.98
     without
    -0.98
     pulsa
    -0.97
    POSITIVE LOGITS
    1.01
     NEEDED
    0.96
     چقدر
    0.95
    anese
    0.94
     verbunden
    0.91
     fathoms
    0.91
    lan
    0.91
     persu
    0.90
     Herbs
    0.90
     olika
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.