© 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. 84194
    Prev
    Next
    INDEX
    Explanations

    trains and locomotives

    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
     Tempest
    -1.21
    筧
    -1.19
     Exploit
    -1.19
    鰐
    -1.17
    alion
    -1.14
    /
    -1.13
    罠
    -1.13
    鉏
    -1.13
    找个
    -1.13
     DISEASES
    -1.12
    POSITIVE LOGITS
     nessun
    1.29
    이스
    1.24
     voglio
    1.24
     trước
    1.23
     porque
    1.17
     has
    1.16
    5
    1.16
     of
    1.16
     ricordo
    1.15
    ungguh
    1.15
    Activations Density 0.020%

    No Known Activations