© 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. 38629
    Prev
    Next
    INDEX
    Explanations

    Improved, Q, Lambda, ;

    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
     Sherman
    -0.77
     almendras
    -0.77
     Strongly
    -0.75
     hives
    -0.74
     Santorini
    -0.73
     kosher
    -0.73
    タル
    -0.71
     ranchers
    -0.71
     ndani
    -0.71
     Gucci
    -0.71
    POSITIVE LOGITS
    ører
    0.93
     addresses
    0.92
    akura
    0.87
     getAddress
    0.83
     address
    0.83
     Совета
    0.82
     paš
    0.82
     addr
    0.79
    Spare
    0.79
     Vázquez
    0.79
    Activations Density 0.003%

    No Known Activations