© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    do your research or chores

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

    The neuron detects mentions of accommodation amenities or features (e.g., Wi-Fi, parking, room fittings, rentals, nearby beaches/airports).

    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
     গ্রহন
    0.50
     zunehm
    0.48
     Tuhan
    0.48
     স্ব
    0.47
     успешно
    0.46
     austen
    0.46
     ṣ
    0.46
     lá
    0.46
     crores
    0.46
     insanlar
    0.46
    POSITIVE LOGITS
     vegetables
    0.53
    器具
    0.50
     전에
    0.49
     shavings
    0.48
     فى
    0.47
     icons
    0.47
     chestnuts
    0.46
    úsica
    0.46
     popcorn
    0.45
    资料
    0.45
    Activations Density 0.071%

    No Known Activations