© 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. 38849
    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
     maksi
    -1.16
    感動
    -1.10
     maji
    -1.03
     kuku
    -1.02
    顏
    -1.01
    hadap
    -1.00
     kela
    -0.99
     this
    -0.99
     without
    -0.98
     mahu
    -0.98
    POSITIVE LOGITS
    u
    1.18
     хотя
    1.15
    also
    1.10
    and
    1.03
    It
    1.02
     sám
    1.01
    WHY
    0.99
    again
    0.99
    ',
    0.97
    porque
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.