© 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. 66148
    Prev
    Next
    INDEX
    Explanations

    And so

    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
    茈
    -1.83
     نیز
    -1.79
     também
    -1.77
    
    -1.77
     entusias
    -1.73
     avancer
    -1.73
     praticamente
    -1.72
     rapidamente
    -1.71
    ſo
    -1.70
     juſ
    -1.70
    POSITIVE LOGITS
     all
    2.13
     just
    2.09
     only
    2.06
     as
    2.02
     ALL
    1.98
     not
    1.96
     most
    1.95
     on
    1.93
     their
    1.88
    ’
    1.87
    Activations Density 0.038%

    No Known Activations