© 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. 86135
    Prev
    Next
    INDEX
    Explanations

    foreign 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
     of
    -1.50
     within
    -1.44
     their
    -1.40
     ajudá
    -1.40
     technischen
    -1.30
     heuti
    -1.29
     wichtigen
    -1.29
     aproveitar
    -1.29
     unangemess
    -1.29
     new
    -1.27
    POSITIVE LOGITS
     színes
    1.53
     dekol
    1.53
    さてさて
    1.43
    diese
    1.41
     个性
    1.34
     článku
    1.32
     gdzie
    1.32
     allt
    1.31
     zprá
    1.30
    atürk
    1.28
    Activations Density 0.251%

    No Known Activations