© 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. 22-GEMMASCOPE-RES-131K
    7. 33733
    Prev
    Next
    INDEX
    Explanations

    repair skin, help maintain, Photoswitching, Q:, function arrow

    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_22/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
     vinaigre
    -1.67
    FontAwesomeIcon
    -1.54
    brtc
    -1.47
    民众
    -1.46
    kadın
    -1.42
     веке
    -1.42
     правительства
    -1.41
     السياس
    -1.36
     officials
    -1.36
    וּ
    -1.34
    POSITIVE LOGITS
     your
    1.71
    ׇ
    1.62
     you
    1.52
     خلال
    1.28
    你在
    1.26
     izvē
    1.23
     сахара
    1.23
     ļoti
    1.20
    netinet
    1.20
     emailAlready
    1.17
    Activations Density 0.018%

    No Known Activations