© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130315
    Prev
    Next
    INDEX
    Explanations

    func, check, describe

    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_22/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
    ｪ
    -0.88
     gänzlich
    -0.87
     persönlichen
    -0.85
     sogenannten
    -0.85
     teljesen
    -0.83
    邏
    -0.81
    完成です
    -0.80
     gän
    -0.80
     großzü
    -0.80
    adə
    -0.79
    POSITIVE LOGITS
    ˑ
    0.90
    黎明
    0.82
    人力
    0.82
     дел
    0.82
     teens
    0.82
    çamento
    0.81
    Dialogs
    0.81
     these
    0.81
    𝟎
    0.81
     slam
    0.79
    Activations Density 0.021%

    No Known Activations