© 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. 53893
    Prev
    Next
    INDEX
    Explanations

    place names and associated entities

    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
     scenarios
    -0.98
     piling
    -0.90
    為什麼
    -0.87
     specially
    -0.87
     discernible
    -0.85
     synonymous
    -0.84
    ضة
    -0.82
    Enrollment
    -0.82
    の為
    -0.81
    scenarios
    -0.81
    POSITIVE LOGITS
     Joint
    1.06
    之际
    0.92
    nel
    0.89
     joint
    0.86
    Joint
    0.82
    joint
    0.78
    THIS
    0.77
    hibit
    0.76
    :+:
    0.75
     Counties
    0.74
    Activations Density 0.100%

    No Known Activations