© 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. 10-GEMMASCOPE-RES-131K
    7. 123894
    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
    2
    -1.58
    8
    -1.36
     же
    -1.34
    ">(</
    -1.27
     chọn
    -1.26
    As
    -1.22
    We
    -1.21
    Il
    -1.20
     rozwo
    -1.20
    4
    -1.19
    POSITIVE LOGITS
     suporta
    1.20
    有机会
    1.16
     wodurch
    1.14
     continúas
    1.13
     daquele
    1.13
    嫑
    1.13
    ンダル
    1.12
    improved
    1.12
    idr
    1.12
     bewilder
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.