© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9935
    Prev
    Next
    INDEX
    Explanations

    lucky outcomes

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

    The main thing this neuron does is detect words conveying luck or fortune.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     EVAL
    0.60
     agonists
    0.56
     نگاه
    0.52
     SOCIAL
    0.51
     praxis
    0.50
    SOCIAL
    0.50
    阂
    0.50
     vigorously
    0.50
    )[:,
    0.49
     sayam
    0.49
    POSITIVE LOGITS
     luck
    3.58
     lucky
    3.39
    lucky
    3.09
     Luck
    3.00
    Luck
    3.00
    luck
    2.97
    Lucky
    2.89
    幸运
    2.89
     LUCKY
    2.84
     Lucky
    2.83
    Activations Density 0.378%

    No Known Activations