© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70992
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     -
    -1.95
    it
    -1.64
    en
    -1.62
    end
    -1.55
    t
    -1.50
    :
    -1.50
    ,
    -1.48
    ed
    -1.46
    ho
    -1.43
     :
    -1.43
    POSITIVE LOGITS
    nemu
    1.64
     katze
    1.52
     装着
    1.50
     canne
    1.48
    Kommentar
    1.47
    jerc
    1.47
    blusa
    1.44
     Rumuni
    1.44
     sprüche
    1.43
     osserv
    1.43
    Activations Density 11.764%

    No Known Activations