© 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. 103654
    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
    というわけで
    -1.34
    餮
    -1.30
    德國
    -1.26
     However
    -1.23
     stycznia
    -1.21
    引用元
    -1.20
     礼物
    -1.18
    ではでは
    -1.15
     їх
    -1.15
    他們
    -1.15
    POSITIVE LOGITS
    
    1.35
     shores
    1.33
    </h5>
    1.29
    </u>
    1.28
    濯
    1.28
    section
    1.26
     Unterschiede
    1.23
     we
    1.22
    इटम
    1.21
    ts
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.