© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75727
    Prev
    Next
    INDEX
    Explanations

    words like

    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
    வும்
    -0.86
    ème
    -0.85
    pagnols
    -0.85
    Jogo
    -0.85
     convertirse
    -0.85
     dispuestos
    -0.82
     unirse
    -0.81
     Appellants
    -0.81
     еще
    -0.80
     يمكنك
    -0.80
    POSITIVE LOGITS
     adev
    0.79
    navigate
    0.78
     derechos
    0.78
     agenda
    0.77
     escon
    0.76
    娯
    0.76
    けれど
    0.74
    stressed
    0.74
     embargo
    0.74
     especí
    0.74
    Activations Density 0.027%

    No Known Activations