© 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. 22-GEMMASCOPE-RES-131K
    7. 9306
    Prev
    Next
    INDEX
    Explanations

    common word pairs

    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_22/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
     two
    -1.32
     that
    -1.14
     organisations
    -1.09
     not
    -1.07
     people
    -1.07
     uffic
    -1.06
     automáticamente
    -1.02
     four
    -1.02
     three
    -1.02
     one
    -1.02
    POSITIVE LOGITS
    Влади
    1.31
    Алексей
    1.27
    ignée
    1.22
     вернуться
    1.20
     kaynağından
    1.20
    lawayo
    1.20
    ać
    1.16
    besondere
    1.16
    Максим
    1.13
    Андрей
    1.12
    Activations Density 0.004%

    No Known Activations