© 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. 45279
    Prev
    Next
    INDEX
    Explanations

    Munich and Bavaria

    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
    龵
    -1.96
     \
    -1.88
    是什么意思
    -1.70
    S
    -1.67
     haji
    -1.67
     acquisto
    -1.56
     veneta
    -1.55
     forskning
    -1.52
    、“
    -1.52
     jaya
    -1.51
    POSITIVE LOGITS
    </h2>
    1.96
     ciento
    1.95
     Bavaria
    1.69
    1.68
    }
    1.67
     treinta
    1.62
    鶫
    1.62
    \\
    1.59
    </h3>
    1.56
    墻
    1.56
    Activations Density 0.021%
    No Known Activations