© 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. 9616
    Prev
    Next
    INDEX
    Explanations

    representing a / observations / healthcare

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

    The neuron fires on function words in explanatory phrases that introduce examples or representation (e.g. “example of,” “representative of,” “reflects”).

    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
    
    0.78
    ל
    0.77
    эл
    0.74
     chatbots
    0.71
    лни
    0.71
    е
    0.70
    не
    0.70
    َل
    0.70
     apprehend
    0.70
    பாளையம்
    0.70
    POSITIVE LOGITS
     suatu
    0.86
     Anfang
    0.80
     achet
    0.80
     собою
    0.80
     ideale
    0.79
     passé
    0.78
     meille
    0.75
     pierre
    0.74
    籤
    0.74
     indiquant
    0.73
    Activations Density 0.277%

    No Known Activations