© 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. 81561
    Prev
    Next
    INDEX
    Explanations

    gasoline prices and subsidies

    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
    હે
    -0.75
    Conrad
    -0.75
    medizin
    -0.74
     hű
    -0.74
    moed
    -0.73
    ucher
    -0.71
    MCE
    -0.71
     cofre
    -0.71
    Skins
    -0.71
     menino
    -0.70
    POSITIVE LOGITS
     PMS
    1.05
     subsidy
    1.00
    pms
    0.95
     бен
    0.84
     queues
    0.82
     Gasoline
    0.82
    PMS
    0.81
     gasoline
    0.81
     Pip
    0.79
    cists
    0.79
    Activations Density 0.002%

    No Known Activations