© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10706
    Prev
    Next
    INDEX
    Explanations

    operators and mathematical symbols

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

    The neuron activates on numeric tokens containing decimal points (e.g. floating-point numbers, often in citations or page/volume metadata).

    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
    ***************
    0.73
    ஃப்
    0.72
     REM
    0.72
     YES
    0.71
     PLEASE
    0.70
    **********
    0.66
     NSE
    0.66
     delimited
    0.66
     பக
    0.65
    **************
    0.64
    POSITIVE LOGITS
     maggiore
    0.90
    üche
    0.80
    olischen
    0.80
    olge
    0.74
     불구
    0.74
     höher
    0.72
    olli
    0.71
    রি
    0.71
    ੌਰ
    0.71
     leichte
    0.71
    Activations Density 0.001%

    No Known Activations