© 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. 22-GEMMASCOPE-RES-131K
    7. 13879
    Prev
    Next
    INDEX
    Explanations

    concluding conjunctions then therefore

    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_22/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
    Altern
    -0.96
    Guer
    -0.93
     Heel
    -0.91
     bete
    -0.90
    ůž
    -0.84
     finan
    -0.83
     пру
    -0.82
     stos
    -0.81
     bes
    -0.81
     conver
    -0.81
    POSITIVE LOGITS
     then
    1.54
    Then
    1.26
     therefore
    1.19
     więc
    1.05
     vergeten
    1.01
     thereby
    0.99
    appartamento
    0.99
     råd
    0.98
     asumir
    0.96
     поэтому
    0.96
    Activations Density 0.045%

    No Known Activations