© 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. 48362
    Prev
    Next
    INDEX
    Explanations

    leader titles and names

    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
     these
    -1.14
     pastors
    -1.07
     dieser
    -1.03
     this
    -1.01
    這種
    -1.00
    這些
    -0.96
     kiş
    -0.93
    錚
    -0.92
    当時は
    -0.92
    套路
    -0.91
    POSITIVE LOGITS
     President
    1.60
     founder
    1.41
    President
    1.33
     Prime
    1.23
     owner
    1.17
     CEO
    1.14
     leader
    1.11
     dictator
    1.07
    Prime
    1.07
     president
    1.05
    Activations Density 0.175%

    No Known Activations