© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9247
    Prev
    Next
    INDEX
    Explanations

    followed by specific terms

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

    The neuron detects promotional or marketing language, flagging words used in selling or offering products and services.

    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
    in
    0.73
     ,\
    0.71
    มอง
    0.69
    
    0.69
    倔
    0.68
    ות
    0.67
    तः
    0.67
     :\
    0.67
    [\
    0.65
    ophobia
    0.65
    POSITIVE LOGITS
     Semester
    0.97
     Soccer
    0.88
     Undergraduate
    0.87
    ណ៌
    0.86
     Públic
    0.84
    同學
    0.84
    同學們
    0.84
     Semaphore
    0.83
     Sted
    0.82
     disponíveis
    0.79
    Activations Density 0.001%

    No Known Activations