© 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. 14864
    Prev
    Next
    INDEX
    Explanations

    symbol or representation

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

    This neuron responds to tokens that are part of proper names or numeric expressions (e.g. titles, personal names, years, or other numbers).

    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
     ৩০
    0.79
     unfamiliar
    0.70
     ۵
    0.70
     ৩
    0.68
     ۲
    0.68
     ২৫
    0.68
     ৫
    0.68
     $*
    0.68
    உங்கள்
    0.68
     ৬
    0.67
    POSITIVE LOGITS
    名字
    0.93
     Literally
    0.87
    的意思
    0.85
     signifying
    0.82
    という意味
    0.80
     symbolizing
    0.79
     symbolizes
    0.79
    意思是
    0.75
    literally
    0.74
     signifies
    0.74
    Activations Density 0.432%

    No Known Activations