© 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. 13057
    Prev
    Next
    INDEX
    Explanations

    related to businesses, developments, team

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

    This neuron detects mentions of accommodation or lodging properties (e.g. “property,” “hotel,” “terrace”) in the text.

    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
    tops
    0.83
    tra
    0.77
    house
    0.76
    times
    0.75
    track
    0.71
    MessageType
    0.71
    Odd
    0.71
    ,
    0.71
     friend
    0.70
    gte
    0.70
    POSITIVE LOGITS
     زیرا
    0.89
     làm
    0.87
     dejando
    0.86
     llegando
    0.85
     Foundations
    0.85
     หลังจาก
    0.85
     입니다
    0.84
     Considerations
    0.84
     consigui
    0.83
    นาง
    0.83
    Activations Density 0.000%

    No Known Activations