© 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. 34-GEMMASCOPE-RES-131K
    7. 92146
    Prev
    Next
    INDEX
    Explanations

    foreign and multilingual text fragments

    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_34/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
    PackageInfo
    -0.88
     javier
    -0.86
    varchar
    -0.82
    WindowConstants
    -0.81
     Colli
    -0.79
     isbn
    -0.79
    eqn
    -0.74
     ldap
    -0.73
     guatemala
    -0.73
    (()
    -0.73
    POSITIVE LOGITS
    なりに
    0.80
     cliente
    0.77
     dovol
    0.73
     Fakten
    0.72
     remit
    0.72
     aconte
    0.71
    の時に
    0.70
     stylu
    0.69
    ُم
    0.69
     faithful
    0.69
    Activations Density 0.180%

    No Known Activations