© 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. 11887
    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
    sandalia
    -1.29
    푔
    -1.25
     anormal
    -1.25
     configurable
    -1.21
     クーポン
    -1.20
     馆
    -1.20
    FXML
    -1.20
     musíte
    -1.19
    ージャー
    -1.18
    itzender
    -1.17
    POSITIVE LOGITS
     recent
    1.16
     significativo
    1.14
     were
    1.14
     tabak
    1.14
    Violence
    1.12
    一套
    1.12
     detenidos
    1.11
    婠
    1.10
    </h3>
    1.09
     beziehungs
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.