© 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. 105582
    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
     esperan
    -1.11
    砵
    -1.05
    镭
    -1.00
    ronomy
    -0.97
    抡
    -0.97
     integrante
    -0.96
     fortale
    -0.95
    閹
    -0.93
    Existe
    -0.93
    魑
    -0.92
    POSITIVE LOGITS
    b
    1.18
    AR
    1.08
    整个
    1.05
    1.01
    B
    1.00
    3
    0.99
    P
    0.97
    F
    0.96
    UC
    0.96
    c
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.