© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21060
    Prev
    Next
    INDEX
    Explanations

    fantasy and magic concepts

    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
     enthou
    -1.33
    餐厅
    -1.29
    ꨄ
    -1.24
    _________
    -1.23
     sommar
    -1.23
    ▪
    -1.22
    스
    -1.19
    createTable
    -1.18
    續
    -1.17
    ____________
    -1.16
    POSITIVE LOGITS
     of
    1.72
     других
    1.19
    ارنة
    1.16
     goggles
    1.15
     you
    1.14
    िये
    1.12
    儒
    1.12
    投入
    1.12
     dipilih
    1.12
    вшие
    1.11
    Activations Density 0.005%

    No Known Activations