© 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. 75644
    Prev
    Next
    INDEX
    Explanations

    list index access

    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
     शुर
    -1.52
    ümüz
    -1.37
     चीज़
    -1.33
    Fornecedor
    -1.30
    我們
    -1.29
     mengucap
    -1.28
    Istorija
    -1.27
    Servico
    -1.27
    ydın
    -1.26
    inį
    -1.25
    POSITIVE LOGITS
     to
    2.34
     also
    2.02
     is
    1.88
     decidedly
    1.75
     already
    1.68
     strikingly
    1.61
     were
    1.52
     of
    1.50
     già
    1.49
     επίσης
    1.47
    Activations Density 0.046%

    No Known Activations