© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6572
    Prev
    Next
    INDEX
    Explanations

    busy/distracted appearance

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

    This neuron strongly activates on words denoting attending or participation in events.

    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
     atmosph
    0.69
     superviv
    0.66
     recoil
    0.63
     dormant
    0.63
     palatable
    0.63
     survive
    0.62
     æ
    0.60
     degraded
    0.60
     temperature
    0.59
     तापमान
    0.59
    POSITIVE LOGITS
    忙
    1.15
     مشغول
    1.12
    Busy
    1.11
     ব্যস্ত
    1.06
    busy
    1.06
     Busy
    1.05
    繁忙
    1.00
     busy
    0.92
     busier
    0.90
     व्यस्त
    0.85
    Activations Density 0.604%

    No Known Activations