© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15880
    Prev
    Next
    INDEX
    Explanations

    Azure, management, Charlie, communications

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

    The neuron strongly activates on standalone numbers and numeric fragments (e.g. model numbers, part codes, measurements).

    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_31_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
    ????????
    0.66
     ????
    0.66
    реза
    0.64
    ################
    0.64
     Initializes
    0.63
     ???
    0.63
    rrrr
    0.61
    bla
    0.61
    !!!!!!!!!!!!!!!!
    0.61
     !!!!!
    0.59
    POSITIVE LOGITS
    
    0.71
    ↵
    0.59
     mivel
    0.55
     adrift
    0.54
    ❘
    0.53
    (-)
    0.53
     tỷ
    0.52
     bijvoorbeeld
    0.52
    燄
    0.52
     hiểm
    0.52
    Activations Density 0.001%

    No Known Activations