© 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. 10-GEMMASCOPE-RES-131K
    7. 11429
    Prev
    Next
    INDEX
    Explanations

    outside of a scope

    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
    (
    -2.83
     ……
    -2.64
     ….
    -2.58
    \
    -2.53
    )
    -2.48
    ");
    -2.34
    .”
    -2.25
    re
    -2.22
    </h2>
    -2.22
    section
    -2.16
    POSITIVE LOGITS
    鷓
    3.17
    狆
    2.86
    鲀
    2.78
    橦
    2.66
    囖
    2.58
    🢒
    2.56
    ਗ਼
    2.55
    獁
    2.52
     ſta
    2.39
    𐐀
    2.39
    Activations Density 0.007%

    No Known Activations