© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    leftovers

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

    The main thing this neuron does is detect numerical quantities (e.g. numbers, percentages, measurements) in the text.

    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
     sefer
    0.55
    нэ
    0.54
    êng
    0.53
    жета
    0.53
    
    0.53
    𒌷
    0.52
     первом
    0.52
     मानो
    0.52
    ӧ
    0.51
    कायदा
    0.51
    POSITIVE LOGITS
     remaining
    4.31
     Remaining
    4.06
    remaining
    4.03
    Remaining
    3.94
    剩下的
    3.61
    剩下
    3.59
    剩余
    3.47
     restante
    3.41
     restantes
    3.38
     অবশিষ্ট
    3.36
    Activations Density 0.714%

    No Known Activations