© 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. 81156
    Prev
    Next
    INDEX
    Explanations

    Keystone XL pipeline

    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
     Winnipeg
    -0.82
     city
    -0.75
     порта
    -0.72
    atamente
    -0.70
     Teach
    -0.69
    Hex
    -0.69
     guía
    -0.68
     biologique
    -0.67
    Teaching
    -0.67
     Teaching
    -0.67
    POSITIVE LOGITS
    Viited
    0.89
     RDP
    0.87
    RDP
    0.78
     automatically
    0.77
     smoothly
    0.76
    cellation
    0.75
    怏
    0.74
    ቀ
    0.74
     Gegensatz
    0.73
    爬
    0.71
    Activations Density 0.015%

    No Known Activations