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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 241
    Prev
    Next
    INDEX
    Explanations

    Radix, empirics, inequalities

    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
    鸶
    -3.16
    ו
    -3.02
    an
    -3.00
    in
    -2.89
    n
    -2.89
    al
    -2.86
     itſelf
    -2.83
    胧
    -2.81
    as
    -2.73
     艺术
    -2.64
    POSITIVE LOGITS
     
    3.09
     i
    2.95
    1
    2.91
     zweite
    2.88
     .
    2.72
    /
    2.72
     e
    2.55
     o
    2.42
     komplette
    2.42
     &
    2.41
    Activations Density 1.232%

    No Known Activations