© 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. 73847
    Prev
    Next
    INDEX
    Explanations

    years or older

    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
     time
    -1.80
     chaque
    -1.66
     енер
    -1.63
    τές
    -1.55
     with
    -1.55
    每个
    -1.49
    
    -1.46
     has
    -1.41
     працю
    -1.39
     each
    -1.38
    POSITIVE LOGITS
    unno
    1.51
    alisco
    1.49
    iempo
    1.44
    有不少
    1.41
    wpdb
    1.41
    lysm
    1.38
     largely
    1.34
    ことです
    1.33
     несколь
    1.31
    hiculo
    1.31
    Activations Density 0.060%

    No Known Activations