© 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. 108423
    Prev
    Next
    INDEX
    Explanations

    Magento laravel Illuminate Symfony Doctrine League

    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
     or
    -0.98
     which
    -0.95
    !!!!!
    -0.94
     seems
    -0.93
     on
    -0.89
    They
    -0.88
    !!!!
    -0.87
     even
    -0.85
     Apparently
    -0.84
    ariant
    -0.81
    POSITIVE LOGITS
    tomorrow
    1.05
    もあった
    1.05
    potentially
    1.03
     bocetos
    1.02
     proyección
    1.02
    atique
    0.97
     trám
    0.96
     smlou
    0.96
     soportes
    0.95
     SHOCK
    0.95
    Activations Density 0.004%

    No Known Activations