© 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. 2459
    Prev
    Next
    INDEX
    Explanations

    Cypress Park

    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
    身后
    -0.79
    🧘
    -0.77
    ijiet
    -0.77
     knocking
    -0.76
    !<
    -0.75
    Stef
    -0.75
     worsen
    -0.75
    nī
    -0.73
     againſt
    -0.73
     characterized
    -0.73
    POSITIVE LOGITS
    Cov
    0.89
    Cover
    0.84
     Cover
    0.83
     Counseling
    0.81
    でも
    0.81
     COVER
    0.80
    Coun
    0.79
     descubrir
    0.79
    粟
    0.76
     rec
    0.75
    Activations Density 0.024%

    No Known Activations