© 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. 86465
    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
     firstly
    -1.49
    鰾
    -1.34
    𓇼
    -1.25
     logically
    -1.24
     only
    -1.22
    <bos>
    -1.21
     sesi
    -1.18
     tonel
    -1.18
     rígido
    -1.16
     abundantly
    -1.15
    POSITIVE LOGITS
     şun
    1.34
    胳
    1.28
    Also
    1.15
    
    1.13
    новь
    1.13
    卅
    1.13
    ayage
    1.12
     کنه
    1.09
     получили
    1.08
    也都
    1.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.