© 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. 8163
    Prev
    Next
    INDEX
    Explanations

    the old covenant

    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
     onCancelled
    -0.71
     مك
    -0.71
    elon
    -0.71
    涪
    -0.70
     Lever
    -0.70
     Is
    -0.69
    小山
    -0.67
     curse
    -0.66
     Budget
    -0.66
     Home
    -0.66
    POSITIVE LOGITS
     IPX
    0.90
    Dex
    0.90
    잠
    0.88
     Dex
    0.86
     Xperia
    0.82
    rijving
    0.82
    Dal
    0.81
    rspec
    0.81
     HTC
    0.81
    dut
    0.80
    Activations Density 0.013%

    No Known Activations