© 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. 22-GEMMASCOPE-RES-131K
    7. 71440
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     eight
    -1.01
     will
    -1.01
    日を
    -0.97
     or
    -0.95
    ستین
    -0.91
    妃
    -0.91
     what
    -0.90
     every
    -0.88
     five
    -0.87
    Unlike
    -0.86
    POSITIVE LOGITS
     花纹
    1.18
     célè
    1.18
     régal
    1.18
     dépens
    1.16
     récol
    1.14
     faciliter
    1.13
     också
    1.10
     patienter
    1.09
     szint
    1.05
     récomp
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.