© 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. 32378
    Prev
    Next
    INDEX
    Explanations

    file content descriptions

    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
     during
    -1.52
     using
    -1.37
     here
    -1.32
     through
    -1.27
     containing
    -1.25
     available
    -1.17
     encompassing
    -1.16
     by
    -1.15
     contains
    -1.13
     During
    -1.13
    POSITIVE LOGITS
     éléments
    1.23
     качестве
    1.15
     بالإضافة
    1.05
     elemente
    1.02
     tage
    0.97
     gea
    0.96
     lunettes
    0.96
     côtes
    0.96
     rau
    0.94
     bords
    0.94
    Activations Density 0.296%

    No Known Activations