© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44225
    Prev
    Next
    INDEX
    Explanations

    javascript const requires

    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
    真的是
    -1.69
     būtų
    -1.67
     zprávy
    -1.62
     naudoti
    -1.57
     tiks
    -1.55
    ್ದ
    -1.55
     Anſ
    -1.52
     großer
    -1.51
    着自己的
    -1.47
     ТАК
    -1.45
    POSITIVE LOGITS
     that
    1.55
     are
    1.48
    ↵
    1.43
     we
    1.41
     and
    1.41
    where
    1.40
     they
    1.40
    |$.
    1.39
     新款
    1.39
     positiva
    1.34
    Activations Density 0.022%

    No Known Activations