© 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. 45555
    Prev
    Next
    INDEX
    Explanations

    towns and communities

    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
     Sydney
    -1.15
     Metro
    -1.09
     Auckland
    -1.06
     Melbourne
    -1.02
     suburban
    -0.95
    Metro
    -0.95
     ilustraciones
    -0.94
    ozo
    -0.93
     лікар
    -0.90
    Auckland
    -0.89
    POSITIVE LOGITS
     town
    1.31
     towns
    1.13
     committees
    0.95
     locals
    0.92
     TOWN
    0.89
     Praça
    0.88
     community
    0.87
     Rural
    0.85
     botas
    0.84
    .•
    0.84
    Activations Density 0.034%

    No Known Activations