© 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. 119809
    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
     you
    -1.14
    2
    -1.05
     I
    -0.91
    いつか
    -0.91
     precede
    -0.88
    5
    -0.88
    だからこそ
    -0.87
    うれしい
    -0.87
     enjoy
    -0.86
     note
    -0.86
    POSITIVE LOGITS
     Mundi
    1.17
     milliard
    1.15
    righted
    1.08
     сс
    1.06
     Sire
    1.03
     Marbella
    1.01
     CONCEPTS
    1.00
    🎨
    1.00
    byg
    1.00
    holiday
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.