© 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. 10-GEMMASCOPE-RES-131K
    7. 129363
    Prev
    Next
    INDEX
    Explanations

    mysterious

    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_10/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
    鶻
    -2.28
     lauded
    -2.25
    </em>
    -2.14
    ){
    -2.11
    o
    -2.11
     '
    -2.09
    >(),
    -2.09
    </strong>
    -2.09
     jarring
    -2.03
    是非常
    -2.02
    POSITIVE LOGITS
    其妙
    2.59
     dorados
    2.45
    vantaged
    2.42
    )’
    2.41
     rojos
    2.41
    ’,
    2.39
    尨
    2.36
    ﱠ
    2.36
    Ꮵ
    2.34
    ness
    2.33
    Activations Density 0.003%

    No Known Activations