© 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. 10-GEMMASCOPE-RES-131K
    7. 8594
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -2.88
      
    -2.73
     "
    -2.69
    (
    -2.47
     '
    -2.42
    The
    -2.42
    T
    -2.41
       
    -2.33
     \
    -2.30
    …
    -2.30
    POSITIVE LOGITS
     çantası
    2.66
     rajut
    2.53
     kılıf
    2.41
    瞜
    2.28
     ビキニ
    2.25
     間取り
    2.22
     špat
    2.17
    注意事
    2.17
     disfraces
    2.16
    ſchen
    2.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.