© 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. 5249
    Prev
    Next
    INDEX
    Explanations

    conditions "about"

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

    The neuron fires on content-bearing words that name or describe abstract concepts (e.g. “interested,” “fiction”).

    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
     فريبيس
    0.73
    IZED
    0.70
     jeopard
    0.70
     obstru
    0.68
    是用
    0.67
    傾
    0.66
     wrongfully
    0.64
     принима
    0.64
     ট্যা
    0.64
     !")
    0.64
    POSITIVE LOGITS
     Lots
    0.91
    Lots
    0.91
     Skyscrapers
    0.86
    Loads
    0.83
    lots
    0.81
    ////////////////
    0.80
    ป
    0.79
    ¾
    0.79
    Congratulations
    0.79
    와
    0.78
    Activations Density 0.000%

    No Known Activations