© 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. 70019
    Prev
    Next
    INDEX
    Explanations

    Christ Church references

    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
    true
    -0.93
    $)
    -0.88
     Nook
    -0.81
     ioe
    -0.80
    recognized
    -0.80
    True
    -0.80
    four
    -0.79
     BOOLEAN
    -0.77
    是否有
    -0.76
    かた
    -0.76
    POSITIVE LOGITS
    سيم
    0.99
    SENT
    0.87
    再
    0.83
     himself
    0.82
     Geburt
    0.81
    سط
    0.79
     there
    0.79
     some
    0.78
     this
    0.78
     Christ
    0.78
    Activations Density 0.019%

    No Known Activations