© 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. 16005
    Prev
    Next
    INDEX
    Explanations

    latex itemize or tabular environments

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

    The neuron consistently fires on standalone numeric expressions—percent signs, decimal numbers, years, volume/page figures—i.e. it detects 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_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
    %%%%%%%%%%%%%
    0.74
    %%%%%%%%%%%%
    0.71
    newpage
    0.66
    fdPar
    0.64
    対称
    0.64
     Lecture
    0.64
    Lecture
    0.64
    textwidth
    0.63
    蜃
    0.62
    %%%%%%%%%%%%%%%%
    0.61
    POSITIVE LOGITS
     TikTok
    0.79
    iktok
    0.79
     tiktok
    0.79
     Tiktok
    0.75
     https
    0.69
     emoji
    0.67
    TikTok
    0.66
     PFAS
    0.66
     influencer
    0.65
     emojis
    0.64
    Activations Density 0.001%

    No Known Activations