© 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. 9700
    Prev
    Next
    INDEX
    Explanations

    professions and titles

    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
     simila
    -1.42
     perioden
    -1.30
    ;
    -1.27
     stoff
    -1.23
     dochter
    -1.22
     lada
    -1.20
    其他的
    -1.20
     wither
    -1.20
     будут
    -1.18
     mètres
    -1.17
    POSITIVE LOGITS
     in
    1.77
     However
    1.58
     at
    1.34
     Однако
    1.28
     of
    1.28
     a
    1.28
     one
    1.27
     There
    1.27
     not
    1.25
    Применение
    1.25
    Activations Density 0.037%

    No Known Activations