© 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. 10-GEMMASCOPE-RES-131K
    7. 10843
    Prev
    Next
    INDEX
    Explanations

    places and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     requerida
    -1.41
    /
    -1.37
     cerrada
    -1.33
    ઃ
    -1.32
     adecuada
    -1.29
    個月
    -1.29
     aislada
    -1.28
    these
    -1.27
    ント
    -1.21
    -
    -1.20
    POSITIVE LOGITS
     have
    1.52
     now
    1.46
     putri
    1.38
     vinos
    1.32
     sexu
    1.30
     garcía
    1.23
     susceptibles
    1.21
     fernández
    1.20
    )))
    1.16
     restau
    1.14
    Activations Density 0.152%

    No Known Activations