© 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. 67922
    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
    HasColumn
    -1.37
    ॰
    -1.31
    OGRAPH
    -1.29
     emporio
    -1.27
     hunde
    -1.27
     where
    -1.25
    洹
    -1.24
     Água
    -1.23
     efficiently
    -1.21
    Fordítás
    -1.19
    POSITIVE LOGITS
    i
    1.16
    o
    1.13
    h
    1.11
     nimmer
    1.10
    j
    1.06
    w
    0.99
     boden
    0.98
    se
    0.98
     verborgen
    0.96
    im
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.