© 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. 9532
    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
    ization
    -1.70
     into
    -1.62
     persino
    -1.48
    蟊
    -1.48
     noten
    -1.47
     tuya
    -1.45
    ться
    -1.45
     путем
    -1.44
    ological
    -1.41
    ,
    -1.40
    POSITIVE LOGITS
    ’
    1.89
    ↵↵
    1.66
    ’:
    1.56
     stronghold
    1.56
     arbeitet
    1.54
    Our
    1.54
     if
    1.49
     centerpiece
    1.49
    荩
    1.48
     zač
    1.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.