© 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. 112014
    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
    妧
    -1.60
     acti
    -1.59
     crucial
    -1.55
    もとも
    -1.55
    ↵
    -1.52
    割と
    -1.48
     reparación
    -1.47
     ______
    -1.45
    neither
    -1.45
     MAIN
    -1.45
    POSITIVE LOGITS
    )
    1.84
    こちらの
    1.59
    这种
    1.56
    ╿
    1.53
    this
    1.52
    these
    1.52
    when
    1.44
    一篇
    1.42
     kullan
    1.41
    These
    1.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.