© 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. 34-GEMMASCOPE-RES-131K
    7. 49122
    Prev
    Next
    INDEX
    Explanations

    titles and quotes

    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_34/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
     поки
    -0.77
    三郎
    -0.75
    imte
    -0.71
     Biochem
    -0.71
    dė
    -0.68
    ([(
    -0.68
     kör
    -0.67
     Sı
    -0.67
     lymp
    -0.67
    umbang
    -0.67
    POSITIVE LOGITS
     Himachal
    0.78
     FaceTime
    0.77
     nativity
    0.77
    عين
    0.76
     jazz
    0.76
    eniem
    0.76
    ophageal
    0.75
    jazz
    0.75
    フォン
    0.75
    olski
    0.74
    Activations Density 0.013%

    No Known Activations