© 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. 34-GEMMASCOPE-RES-131K
    7. 102717
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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_34/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
     exatamente
    -0.99
    愆
    -0.95
    rifice
    -0.92
     وكذلك
    -0.90
     @}
    -0.85
    CommonModule
    -0.85
    啬
    -0.84
    ọi
    -0.84
    TOGGLE
    -0.84
    "./
    -0.84
    POSITIVE LOGITS
     بخ
    0.77
     namelijk
    0.75
    NTSTATUS
    0.74
    rzu
    0.73
    エレ
    0.72
     Engineer
    0.71
    configFile
    0.69
    pozdrawiam
    0.69
     emphas
    0.68
    Engineer
    0.68
    Activations Density 0.032%

    No Known Activations