© 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. 109461
    Prev
    Next
    INDEX
    Explanations

    -art ending words and names

    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
     nghiệm
    -0.91
    otimes
    -0.84
    Dermal
    -0.71
     infek
    -0.70
     asbestos
    -0.70
     battalion
    -0.70
    싶
    -0.68
    ̙
    -0.68
    atore
    -0.67
     fedora
    -0.66
    POSITIVE LOGITS
    START
    1.22
    car
    1.21
     bar
    1.19
    าร์
    1.18
    spark
    1.18
     Park
    1.16
    bart
    1.15
    art
    1.15
    scar
    1.15
    zar
    1.13
    Activations Density 0.038%

    No Known Activations