© 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. 10-GEMMASCOPE-RES-131K
    7. 1421
    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
    The
    -3.34
    We
    -2.92
     Utilizing
    -2.88
    This
    -2.84
     Upon
    -2.70
    Через
    -2.70
     Presently
    -2.69
    傒
    -2.69
     Commonly
    -2.69
     Currently
    -2.64
    POSITIVE LOGITS
     to
    2.92
    ↵
    2.73
     and
    2.69
    鼍
    2.33
    kräfte
    2.25
     greateſt
    2.20
     ему
    2.19
     также
    2.14
    髕
    2.11
     飾り
    2.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.