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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 590
    Prev
    Next
    INDEX
    Explanations

    units and measurements

    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
     to
    -2.67
     their
    -2.59
     that
    -2.02
    ℟
    -1.72
     the
    -1.68
     some
    -1.43
     tijdens
    -1.41
     Quiero
    -1.39
     durante
    -1.38
    etsy
    -1.38
    POSITIVE LOGITS
     estatua
    1.80
     dekoratif
    1.71
     way
    1.70
     thing
    1.59
    şem
    1.58
     οποία
    1.56
     cristales
    1.54
     bolsillos
    1.54
     but
    1.47
    second
    1.45
    Activations Density 0.046%

    No Known Activations