© 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. 70598
    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
    mű
    -1.10
     stronghold
    -1.08
    ronomie
    -1.06
    denk
    -1.05
     kadın
    -1.05
     encontro
    -1.01
    getF
    -1.00
     misspelled
    -1.00
    휼
    -0.99
    baarheid
    -0.97
    POSITIVE LOGITS
    The
    1.00
     should
    0.96
     at
    0.96
     believe
    0.95
     then
    0.94
    alez
    0.92
     know
    0.90
    ませんが
    0.88
     Section
    0.87
    ®,
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.