© 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. 45263
    Prev
    Next
    INDEX
    Explanations

    Device Under Test (DUT)

    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
    गा
    -0.77
    ieważ
    -0.75
     Abdomen
    -0.72
    Semana
    -0.70
    坚持
    -0.68
    ⟷
    -0.68
     HSA
    -0.68
    Smack
    -0.67
     Voir
    -0.66
    Synonymes
    -0.66
    POSITIVE LOGITS
     under
    2.52
     SUT
    2.36
     DUT
    2.17
    under
    2.09
    sut
    2.09
     sut
    2.08
     tested
    2.05
    Under
    2.03
     Under
    1.97
    DUT
    1.91
    Activations Density 0.091%

    No Known Activations