© 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. 25668
    Prev
    Next
    INDEX
    Explanations

    historical expeditions and wars

    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
     samples
    -0.78
    ínas
    -0.71
    日は
    -0.71
    鍼
    -0.70
     uncontrolled
    -0.69
    ΙΑ
    -0.69
    Переваги
    -0.68
     понравилось
    -0.68
     introduce
    -0.68
     doses
    -0.67
    POSITIVE LOGITS
     campaign
    2.70
     campaigns
    2.52
    campaign
    2.23
     crusade
    2.09
    Campaign
    2.02
     Campaigns
    1.93
     Campaign
    1.92
    campaigns
    1.86
     expedition
    1.80
     CAMPAIGN
    1.75
    Activations Density 0.033%

    No Known Activations