© 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. 74707
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    鋨
    -2.02
     ativos
    -1.88
     gerais
    -1.84
    書の
    -1.75
     utilisées
    -1.72
    ᠂
    -1.72
    la
    -1.70
    ーーー
    -1.66
    了过来
    -1.65
     新款
    -1.64
    POSITIVE LOGITS
     llorando
    1.79
     để
    1.79
     tuviera
    1.77
     of
    1.63
    はこの
    1.61
    赑
    1.60
     untuk
    1.59
    曖
    1.57
     muerta
    1.57
     fieltro
    1.57
    Activations Density 0.013%

    No Known Activations