© 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. 93749
    Prev
    Next
    INDEX
    Explanations

    Australian statistical data and reports

    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
    Provincial
    -0.77
     ciep
    -0.75
     arvo
    -0.71
     ihan
    -0.68
    /?
    -0.68
    colours
    -0.67
     Province
    -0.66
    Defender
    -0.66
    修为
    -0.66
    $^{-
    -0.66
    POSITIVE LOGITS
     Australia
    0.93
    Australia
    0.84
    noc
    0.84
     Australian
    0.82
    ↝
    0.79
     imprisonment
    0.79
     régal
    0.79
    berte
    0.78
    yczne
    0.77
    НОСТИ
    0.77
    Activations Density 0.020%

    No Known Activations