© 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. 74561
    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
     когда
    -1.27
    when
    -1.24
     stie
    -1.20
     varones
    -1.18
    ).
    -1.07
     aft
    -1.07
     cuando
    -1.06
     When
    -1.06
     ketika
    -1.05
    ின்
    -1.03
    POSITIVE LOGITS
     stejně
    1.07
     outono
    1.03
    řej
    1.01
     imprescin
    0.98
    在这个
    0.98
     الأخيرة
    0.97
    목
    0.97
    在
    0.96
    edipus
    0.96
    
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.