© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73738
    Prev
    Next
    INDEX
    Explanations

    vice vs 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
     krem
    -1.09
    iedad
    -1.02
    ==="
    -0.98
    ᵢ
    -0.96
    nání
    -0.95
    ²)
    -0.93
     וי
    -0.92
    Hugh
    -0.92
     klik
    -0.91
     Jacques
    -0.90
    POSITIVE LOGITS
     Bolsonaro
    1.12
     Netanyahu
    1.02
     Obama
    1.00
     Schwarzenegger
    0.99
     van
    0.94
    Putin
    0.94
     Putin
    0.93
     Springsteen
    0.93
     Smith
    0.90
    Obama
    0.90
    Activations Density 0.107%

    No Known Activations