© 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. 1274
    Prev
    Next
    INDEX
    Explanations

    demonstratives across languages

    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
     will
    -1.30
     if
    -1.30
     henkilö
    -1.20
     abbildung
    -1.20
    šky
    -1.18
     åp
    -1.18
    𝄇
    -1.17
     condenado
    -1.16
     protože
    -1.16
     there
    -1.15
    POSITIVE LOGITS
     estos
    1.31
    ൺ
    1.20
     these
    1.20
     alſo
    1.20
     ſome
    1.20
     Tämä
    1.16
     veramente
    1.16
    شناسی
    1.14
     kjer
    1.13
     mangá
    1.08
    Activations Density 0.263%

    No Known Activations