© 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. 71069
    Prev
    Next
    INDEX
    Explanations

    mathematical constants or parameters

    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
    jand
    -1.30
    拚
    -1.16
     Polar
    -1.16
    𓆏
    -1.16
     zj
    -1.16
     skole
    -1.15
     yayın
    -1.15
     sinta
    -1.14
    ྃ
    -1.14
     procent
    -1.12
    POSITIVE LOGITS
     there
    1.50
     it
    1.35
     為
    1.28
     слишком
    1.27
     sanitarias
    1.24
     там
    1.23
    Проце
    1.20
     científicas
    1.16
    或者
    1.15
     Họ
    1.15
    Activations Density 0.043%

    No Known Activations