© 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. 65701
    Prev
    Next
    INDEX
    Explanations

    earning money to survive

    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
    nému
    -0.85
     trám
    -0.82
     quà
    -0.82
    mening
    -0.81
    nO
    -0.81
     sólidos
    -0.80
     gier
    -0.79
     ling
    -0.79
     aider
    -0.77
    fto
    -0.76
    POSITIVE LOGITS
     survive
    1.95
     paying
    1.93
     ends
    1.65
     survival
    1.59
     pay
    1.58
     pays
    1.53
    Paying
    1.48
     keep
    1.47
     meet
    1.44
     make
    1.43
    Activations Density 0.028%

    No Known Activations