© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 313
    Prev
    Next
    INDEX
    Explanations

    culture and place

    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
     Eindruck
    -1.73
     Of
    -1.71
    anyeol
    -1.67
    鯪
    -1.66
    ･･
    -1.64
     bekämp
    -1.62
    　＊
    -1.57
    縠
    -1.55
    ambut
    -1.54
    塍
    -1.53
    POSITIVE LOGITS
    </h4>
    2.19
    on
    1.78
     besök
    1.70
    </b>
    1.66
    f
    1.60
    tu
    1.57
    0
    1.54
     }
    1.52
    子的
    1.48
    cie
    1.46
    Activations Density 0.015%

    No Known Activations