© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 2657
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    The neuron strongly activates on tokens that are numeric values (including multi‐digit numbers and decimals).

    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
     empezamos
    0.61
    
    0.57
    䡊
    0.57
    hereafter
    0.57
     (“
    0.55
     encontramos
    0.55
     dvě
    0.54
     প্রথমেই
    0.54
    ड़ब
    0.54
    ֜
    0.54
    POSITIVE LOGITS
    <eos>
    4.09
    ៕
    2.47
     继续访问
    1.68
    </blockquote>
    1.33
    <unused63>
    1.24
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.22
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.17
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.17
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.16
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.16
    Activations Density 2.028%

    No Known Activations