© 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. 79907
    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
     both
    -1.26
     their
    -1.15
     even
    -1.04
     Solidar
    -1.00
     last
    -0.95
     россия
    -0.90
     Toh
    -0.89
     butik
    -0.87
     whichever
    -0.85
     isolating
    -0.84
    POSITIVE LOGITS
     meninos
    1.23
    🅵
    1.06
    ська
    1.03
     треба
    1.02
     Selanjutnya
    1.01
    ിൽ
    1.00
    ンク
    0.99
     não
    0.97
     lò
    0.96
     WITHIN
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.