© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76680
    Prev
    Next
    INDEX
    Explanations

    happiness and contentment

    np_acts-logits-general · gemini-2.5-flash-lite

    happiness versus wealth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruits
    0.49
    动脉
    0.47
    頡
    0.46
    lumat
    0.45
     डाउट्स
    0.44
    咘
    0.44
    कार्ट
    0.43
    锐
    0.43
    报错
    0.42
    肃
    0.42
    POSITIVE LOGITS
     happiness
    1.18
     Happiness
    1.10
    happiness
    1.05
     felicidade
    1.00
     felicidad
    0.99
    Happiness
    0.96
    幸福
    0.95
     сча
    0.95
     contentment
    0.93
     সুখী
    0.92
    Activations Density 0.165%

    No Known Activations