© 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. 10-GEMMASCOPE-RES-131K
    7. 86432
    Prev
    Next
    INDEX
    Explanations

    floating point precision and format

    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_10/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
     it
    -2.11
     Unterschiede
    -1.40
     same
    -1.39
     e
    -1.38
     Bedürfnisse
    -1.37
     él
    -1.34
     ‘
    -1.30
     besondere
    -1.30
    ."
    -1.28
     would
    -1.27
    POSITIVE LOGITS
     становятся
    1.37
    gyű
    1.35
    gesamt
    1.32
    ADORES
    1.27
    ***********
    1.26
     Rø
    1.25
     &,
    1.23
    achusetts
    1.19
    geschenk
    1.19
    flüge
    1.17
    Activations Density 0.050%

    No Known Activations