© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60115
    Prev
    Next
    INDEX
    Explanations

    code comments and markup

    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
     of
    -1.81
     where
    -1.55
    是我们
    -1.53
     où
    -1.50
    我們
    -1.43
    已經
    -1.35
    ære
    -1.34
    在我
    -1.31
    已
    -1.30
    続けて
    -1.20
    POSITIVE LOGITS
     mesta
    1.63
    imantan
    1.55
    ⬤
    1.55
     endearing
    1.55
    賔
    1.54
     unwavering
    1.52
     требо
    1.51
     conquista
    1.49
     both
    1.48
    もはや
    1.48
    Activations Density 0.001%

    No Known Activations