© 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. 113347
    Prev
    Next
    INDEX
    Explanations

    CrossFit and fitness exercises

    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
    神情
    -1.36
     TWENTY
    -1.36
    还是很
    -1.35
     самы
    -1.35
    慙
    -1.33
    臜
    -1.30
    dious
    -1.30
    神
    -1.23
    decla
    -1.22
    そういった
    -1.22
    POSITIVE LOGITS
     candidatura
    1.31
     triliun
    1.19
    恙
    1.16
     Only
    1.16
     patrimonio
    1.13
     csak
    1.12
     Revista
    1.11
    ях
    1.11
     just
    1.09
     می‌کنند
    1.09
    Activations Density 0.026%

    No Known Activations