© 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. 34854
    Prev
    Next
    INDEX
    Explanations

    street addresses and zip codes

    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
    上げて
    -0.99
    েই
    -0.87
     雞
    -0.85
     because
    -0.84
    ⁱ
    -0.82
    （※
    -0.81
     even
    -0.80
     raising
    -0.79
     helping
    -0.78
    东京
    -0.77
    POSITIVE LOGITS
     downtown
    1.05
    Antworten
    0.90
    Downtown
    0.88
    演唱
    0.85
    ða
    0.83
    locu
    0.83
    Exceptional
    0.82
    downtown
    0.79
     city
    0.78
     Downtown
    0.77
    Activations Density 0.012%

    No Known Activations