© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5987
    Prev
    Next
    INDEX
    Explanations

    technical specifications and summaries

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

    The neuron is triggered by long runs of whitespace or indentation spacing 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
    いたり
    0.64
    kje
    0.64
    ektor
    0.62
    스크
    0.62
     contas
    0.60
    쪽
    0.59
    ych
    0.58
    ять
    0.57
    टने
    0.57
    សម
    0.57
    POSITIVE LOGITS
      
    0.88
    між
    0.72
    <0xC2>
    0.68
     বিচারপতি
    0.66
    Від
    0.65
    Ibid
    0.64
    Gambar
    0.63
     Verlag
    0.63
    心配
    0.63
       
    0.62
    Activations Density 0.016%

    No Known Activations