© 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. 23570
    Prev
    Next
    INDEX
    Explanations

    javascript libraries and frameworks

    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
    سياسي
    -0.85
     Euro
    -0.83
    ůměr
    -0.82
    чья
    -0.81
     SQL
    -0.80
    boston
    -0.80
     styles
    -0.79
    arxiv
    -0.79
     chi
    -0.79
     data
    -0.79
    POSITIVE LOGITS
     juf
    0.94
     entusias
    0.93
     rencontr
    0.91
    Katalog
    0.90
     oslo
    0.88
     possesso
    0.88
    Archite
    0.87
     contagio
    0.86
    宗教
    0.86
     religi
    0.86
    Activations Density 0.051%

    No Known Activations