© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107239
    Prev
    Next
    INDEX
    Explanations

    envy and jealousy

    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
     штра
    -0.82
    incident
    -0.81
    issent
    -0.81
    ("."
    -0.79
    feedback
    -0.79
     Refund
    -0.78
    undrum
    -0.77
     refunded
    -0.76
     refunds
    -0.76
    Feedback
    -0.76
    POSITIVE LOGITS
     jealous
    5.06
     jealousy
    4.84
     Jealous
    4.16
     envy
    4.03
     envious
    3.80
    Jealous
    3.77
     Envy
    2.75
    嫉妒
    2.16
     зави
    2.03
     envies
    2.00
    Activations Density 0.036%

    No Known Activations