© 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. 34760
    Prev
    Next
    INDEX
    Explanations

    mathematical limits

    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
    Ų
    -0.72
    嵬
    -0.69
    шается
    -0.69
    colate
    -0.68
     vélos
    -0.67
    cute
    -0.67
     damski
    -0.66
     Ahn
    -0.66
    burton
    -0.66
    atet
    -0.66
    POSITIVE LOGITS
     limit
    4.91
    lim
    4.09
     limits
    4.03
    limit
    3.98
     lim
    3.83
     Limit
    3.69
    LIMIT
    3.66
    Limit
    3.64
     LIMIT
    3.53
     limite
    3.36
    Activations Density 0.057%

    No Known Activations