© 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. 98572
    Prev
    Next
    INDEX
    Explanations

    New Zealand locations

    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
     Christchurch
    -0.92
     Otago
    -0.87
    Auckland
    -0.86
     Wellington
    -0.85
     Auckland
    -0.84
    くなった
    -0.73
    charging
    -0.71
    采
    -0.70
     Commonwealth
    -0.69
    ют
    -0.69
    POSITIVE LOGITS
     Aene
    0.82
     TAMB
    0.81
     Mesin
    0.81
    Sao
    0.79
    ligne
    0.78
    minaire
    0.76
    Juri
    0.76
     Լ
    0.75
    SETTINGS
    0.75
     SWR
    0.75
    Activations Density 0.037%

    No Known Activations