© 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. 73971
    Prev
    Next
    INDEX
    Explanations

    list items

    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
     to
    -1.16
     dangereux
    -1.01
     aldri
    -0.88
    who
    -0.88
    一旁
    -0.87
    new
    -0.87
    それに
    -0.84
    一條
    -0.84
     répand
    -0.84
    user
    -0.83
    POSITIVE LOGITS
    []
    1.03
     camión
    1.00
    ૪
    0.99
     befes
    0.95
    ngrx
    0.95
    Biografia
    0.94
     both
    0.94
    Capítulo
    0.94
     (!__
    0.93
     zowel
    0.91
    Activations Density 0.098%

    No Known Activations