© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13784
    Prev
    Next
    INDEX
    Explanations

    historical, emotional, triggered

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

    The neuron fires on expressions of hope or encouraging expectations (e.g. “hope,” “hopefully”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ्यूड
    0.55
    体验
    0.52
    臻
    0.51
     체험
    0.50
    身上
    0.50
    體驗
    0.50
     新作
    0.49
     любое
    0.49
    >'
    0.49
     supplément
    0.48
    POSITIVE LOGITS
    ря
    0.59
     willen
    0.57
    ƙ
    0.57
     volts
    0.57
     fuerzas
    0.55
     consulte
    0.55
    acles
    0.55
     gases
    0.55
     harmonics
    0.54
     discount
    0.54
    Activations Density 0.000%

    No Known Activations