© 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. 10402
    Prev
    Next
    INDEX
    Explanations

    everything from

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

    The neuron strongly activates on the word “everything.”

    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
    𝚜
    0.80
    SendCommand
    0.72
     какого
    0.71
    Representation
    0.70
    something
    0.70
    졌
    0.70
    SCHOOL
    0.69
    Ở
    0.68
    삿
    0.68
    띠
    0.68
    POSITIVE LOGITS
     else
    1.07
     Else
    0.90
     Everything
    0.81
     cellulose
    0.78
     imaginable
    0.75
     everything
    0.71
     except
    0.70
    cyte
    0.70
     compris
    0.70
     artisanal
    0.70
    Activations Density 0.105%

    No Known Activations