© 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. 774
    Prev
    Next
    INDEX
    Explanations

    city and town 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
     methods
    -0.95
     questions
    -0.93
     並
    -0.90
     examples
    -0.90
     understand
    -0.86
     trasporto
    -0.83
    風味
    -0.83
     trato
    -0.82
    ívar
    -0.82
     improved
    -0.80
    POSITIVE LOGITS
     City
    1.24
     Moines
    1.23
    ville
    1.20
     Springs
    1.20
     CITY
    1.14
    VILLE
    1.12
    ipzig
    1.12
    tsburgh
    1.09
    stown
    1.06
    ensburg
    1.05
    Activations Density 0.347%

    No Known Activations