© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12954
    Prev
    Next
    INDEX
    Explanations

    positive emotions and anticipation

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

    The neuron strongly responds to words expressing high-arousal excitement or eager, energetic anticipation.

    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_24_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
    เสียหาย
    0.73
     проблемы
    0.68
    损害
    0.67
     проблему
    0.65
    yta
    0.65
    䢙
    0.64
    逪
    0.64
    桻
    0.64
    serious
    0.63
    नात्मक
    0.63
    POSITIVE LOGITS
     excitedly
    0.96
     anticipation
    0.86
     dread
    0.80
     anxiously
    0.80
     reminis
    0.79
     cravings
    0.78
     excitement
    0.78
     dreaded
    0.77
     nostalgia
    0.75
     eagerly
    0.75
    Activations Density 0.392%

    No Known Activations