© 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. 32259
    Prev
    Next
    INDEX
    Explanations

    of the form

    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
     deporte
    -0.78
    材質
    -0.77
     بك
    -0.76
     Sparta
    -0.74
    rouch
    -0.74
     Barclays
    -0.73
     rique
    -0.73
    只见
    -0.72
    Encu
    -0.70
    )>=
    -0.70
    POSITIVE LOGITS
     form
    2.05
    形
    1.69
     dạng
    1.55
     postaci
    1.48
     of
    1.39
     type
    1.30
     вида
    1.30
     форме
    1.28
    form
    1.27
    的形式
    1.27
    Activations Density 0.080%

    No Known Activations