© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7280
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     said
    -1.21
     whom
    -1.16
    ของ
    -1.03
     ;
    -1.03
    該当
    -1.02
     infancia
    -1.00
     ส์
    -1.00
     also
    -0.99
    رى
    -0.98
     soorten
    -0.97
    POSITIVE LOGITS
     norvég
    1.27
     amerik
    1.16
    过敏
    1.13
     foton
    1.12
     lü
    1.12
     eksemp
    1.09
     peluche
    1.09
     türk
    1.09
    激素
    1.09
     deng
    1.08
    Activations Density 0.151%

    No Known Activations