© 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. 92258
    Prev
    Next
    INDEX
    Explanations

    names, places, and technical terms

    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
    ẵ
    -0.84
    祖国
    -0.83
     meny
    -0.82
     atletas
    -0.82
    ição
    -0.81
     ي
    -0.80
    ENTIALS
    -0.79
    >-</
    -0.79
     Meksiku
    -0.79
    UnknownFields
    -0.79
    POSITIVE LOGITS
    Kentucky
    1.21
     Kentucky
    1.02
     zweck
    0.88
     dầu
    0.84
     офі
    0.81
    這樣
    0.79
     neumáticos
    0.78
    Музыка
    0.77
     außerord
    0.77
    meteor
    0.76
    Activations Density 0.000%

    No Known Activations