© 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. 54001
    Prev
    Next
    INDEX
    Explanations

    questions and phrases

    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
     THING
    -0.96
     této
    -0.94
     ネイビー
    -0.90
     cerâmica
    -0.88
     ansiedad
    -0.87
     dentes
    -0.83
    andai
    -0.82
    nene
    -0.82
    "],
    -0.82
     laranja
    -0.81
    POSITIVE LOGITS
     dolor
    0.88
     gelatin
    0.87
    粉絲
    0.85
    ❉
    0.83
    tido
    0.82
     indignation
    0.80
    bonucle
    0.80
     mares
    0.79
     ला
    0.78
    心头
    0.77
    Activations Density 0.001%

    No Known Activations