© 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. 8231
    Prev
    Next
    INDEX
    Explanations

    percentage rates annually

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

    The neuron strongly activates on numeric percentage expressions.

    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
     ['',
    0.55
    
    0.55
     (!)
    0.54
     unwitting
    0.52
    ">—
    0.52
    当量
    0.51
    -(-
    0.50
    董事
    0.50
    হেতু
    0.49
     नवी
    0.49
    POSITIVE LOGITS
     chapel
    0.62
     mw
    0.61
     acrylic
    0.59
     উত্তেজ
    0.59
     ver
    0.57
     Acrylic
    0.57
     তাও
    0.57
    áb
    0.56
     КАК
    0.56
    டத்தில்
    0.56
    Activations Density 0.000%

    No Known Activations