© 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. 27095
    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
     Reſ
    -1.36
     relacionamento
    -1.36
     ſeveral
    -1.35
    pecabe
    -1.30
     sordid
    -1.29
     compromisso
    -1.29
     Inſ
    -1.25
     domínio
    -1.22
    其他
    -1.21
     prized
    -1.19
    POSITIVE LOGITS
     linkovi
    1.15
     고
    1.13
    udahkan
    1.08
    võ
    1.05
     mân
    1.05
     llegue
    1.05
    ですが
    1.03
     COMPOUNDS
    1.02
    我们的
    1.00
    Воспита
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.