© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85021
    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
     nét
    -1.05
    CLAIM
    -1.04
     bekerja
    -1.03
     glä
    -1.02
     الحرب
    -1.02
    bộ
    -1.01
     adquis
    -1.00
    riedenheit
    -1.00
    闈
    -0.99
    🦾
    -0.99
    POSITIVE LOGITS
     of
    1.37
    In
    1.09
     these
    0.94
    <h1>
    0.90
    !!!”
    0.90
    igos
    0.88
    !!”
    0.88
     comprises
    0.88
     such
    0.85
    ごちそう
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.