© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6929
    Prev
    Next
    INDEX
    Explanations

    vehicle mirrors and cameras

    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
    Negative Logits
    llingwood
    -1.46
     beroep
    -1.44
    ykjav
    -1.35
    -
    -1.34
     geholfen
    -1.32
    zelfde
    -1.30
    渽
    -1.29
    望着
    -1.26
    ſam
    -1.24
     vorigen
    -1.23
    POSITIVE LOGITS
    پرس
    1.41
     any
    1.41
    ಗಳು
    1.38
    清晰
    1.33
     από
    1.30
     شیپور
    1.29
    siyon
    1.29
    koli
    1.28
     alerg
    1.27
     descans
    1.26
    Activations Density 0.013%

    No Known Activations