© 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. 22-GEMMASCOPE-RES-131K
    7. 12476
    Prev
    Next
    INDEX
    Explanations

    data structures and code

    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_22/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
    が
    -0.91
     will
    -0.91
    \",
    -0.88
     એ
    -0.85
    皿
    -0.83
    مصادر
    -0.83
    дів
    -0.82
    ţiile
    -0.82
    を
    -0.81
     did
    -0.79
    POSITIVE LOGITS
     pagado
    0.90
     viață
    0.90
    毘
    0.83
     Дей
    0.82
     entonces
    0.82
    と書
    0.80
    zedł
    0.79
     jusqu
    0.79
    Rptr
    0.78
    beginning
    0.77
    Activations Density 0.053%

    No Known Activations