© 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. 92416
    Prev
    Next
    INDEX
    Explanations

    justin followed by name

    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
     Bogota
    -0.78
     bathroom
    -0.78
    otriva
    -0.76
     breweries
    -0.75
    teck
    -0.75
     contagios
    -0.74
     Serp
    -0.73
     isang
    -0.73
    tians
    -0.73
    thus
    -0.72
    POSITIVE LOGITS
    四个
    0.77
     развития
    0.75
    同様に
    0.74
    に追加
    0.73
     ofreciendo
    0.73
    ourge
    0.72
     unjust
    0.71
    OrEmpty
    0.71
     allá
    0.70
     Injuries
    0.68
    Activations Density 0.021%

    No Known Activations