© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7523
    Prev
    Next
    INDEX
    Explanations

    physical soreness

    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
     We
    -2.56
    ꜛ
    -2.53
     dañ
    -2.48
     copias
    -2.42
    ৄ
    -2.41
     oraz
    -2.39
     Now
    -2.31
    韡
    -2.28
    ungkinkan
    -2.25
    窳
    -2.25
    POSITIVE LOGITS
    葙
    2.80
    ↵↵
    2.64
    躝
    2.59
    r
    2.55
    re
    2.53
    </h3>
    2.42
    '
    2.33
    ꜆
    2.22
    餮
    2.20
     visse
    2.19
    Activations Density 0.002%

    No Known Activations