© 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. 58962
    Prev
    Next
    INDEX
    Explanations

    stimulus and relief packages

    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
     прогно
    -0.82
    ǫ
    -0.77
    
    -0.77
    ierr
    -0.75
     elevador
    -0.75
    世纪
    -0.74
    密码
    -0.73
     Tennyson
    -0.73
    一口
    -0.72
    ßten
    -0.71
    POSITIVE LOGITS
     aid
    1.38
     stimulus
    1.37
     Coronavirus
    1.18
     coronavirus
    1.10
     unemployment
    1.07
     CAR
    1.07
     relief
    1.07
     assistance
    1.05
    Coronavirus
    1.05
     Stimulus
    1.04
    Activations Density 0.006%

    No Known Activations