© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59486
    Prev
    Next
    INDEX
    Explanations

    main followed by location or feature

    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
    generally
    -1.26
    primarily
    -1.23
    becomes
    -1.18
    Mvh
    -1.18
    鲠
    -1.16
    considering
    -1.12
    モバイル
    -1.05
    mvh
    -1.05
    indicates
    -1.04
    鮰
    -1.04
    POSITIVE LOGITS
     main
    1.49
     part
    1.41
     body
    1.35
     three
    1.32
     four
    1.29
     two
    1.27
    frame
    1.24
     eight
    1.23
     portion
    1.20
     it
    1.18
    Activations Density 0.036%

    No Known Activations