© 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. 12467
    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
     varför
    -1.16
     remainder
    -1.11
    だろうか
    -1.09
     largest
    -1.09
     跳转
    -1.09
    ですかね
    -1.07
     dagelijks
    -1.06
    踴
    -1.05
    dreamstime
    -1.03
     розташо
    -1.03
    POSITIVE LOGITS
     '
    1.45
    ».
    1.16
    ("
    1.16
     «
    1.15
    
    1.14
     pão
    1.12
     verdient
    1.12
    ‫
    1.10
     ñ
    1.10
    ___________
    1.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.