© 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. 60775
    Prev
    Next
    INDEX
    Explanations

    company suffixes or domains

    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
     impresionantes
    -1.94
     mascarilla
    -1.93
     sabias
    -1.87
     gastronomía
    -1.84
     saludables
    -1.80
     artesanía
    -1.75
     manguera
    -1.68
     calientes
    -1.66
     feiner
    -1.63
     almohada
    -1.62
    POSITIVE LOGITS
     with
    2.73
     to
    2.17
     barnet
    1.94
    though
    1.84
     bahkan
    1.70
     televisi
    1.63
    洸
    1.59
    рой
    1.56
    𓂂
    1.53
    although
    1.52
    Activations Density 1.401%

    No Known Activations