© 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. 112039
    Prev
    Next
    INDEX
    Explanations

    nyholy/nyart/nytesta/nyco/nyan

    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
    .
    -3.08
    ?”
    -2.73
     disposto
    -2.69
    al
    -2.20
    烀
    -2.16
    ++)
    -2.16
    ↵
    -2.16
     главным
    -2.11
    饃
    -2.09
    襌
    -2.09
    POSITIVE LOGITS
    嗐
    2.83
    ."
    2.38
     sarcastic
    2.22
    )
    2.20
    nisses
    2.19
     bolster
    2.14
    !"
    2.13
     belligerent
    2.11
     staunch
    2.09
     makeshift
    2.09
    Activations Density 0.009%

    No Known Activations