© 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. 22-GEMMASCOPE-RES-131K
    7. 39253
    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
     by
    -1.52
     function
    -1.21
     souhaite
    -1.18
    -1.16
     vivía
    -1.16
     almohada
    -1.15
     information
    -1.15
    手続き
    -1.13
     guarantees
    -1.12
     television
    -1.11
    POSITIVE LOGITS
    ೫
    1.52
    ೮
    1.52
    不管是
    1.44
     trabalhando
    1.33
    无论是
    1.31
    辊
    1.26
    دانلود
    1.25
     erwähnten
    1.25
     Allerdings
    1.22
    ೩
    1.22
    Activations Density 0.000%
    No Known Activations
    This feature has no known activations.