© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14540
    Prev
    Next
    INDEX
    Explanations

    handle water flow

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

    The neuron fires most strongly on quantifier or measurement terms—words or multiword tokens that express counts, amounts, or quantities.

    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_24_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
     這個
    0.90
    ح
    0.81
     ใน
    0.80
     وهذا
    0.77
     เมื่อ
    0.75
     แล
    0.75
    ំន
    0.75
     במ
    0.74
     จาก
    0.73
    IT
    0.73
    POSITIVE LOGITS
    ことなく
    0.79
     CpG
    0.77
     sulfon
    0.74
    旌
    0.74
     automaker
    0.73
     tremor
    0.73
     PFAS
    0.73
    配信
    0.73
     boreal
    0.73
    梢
    0.72
    Activations Density 0.000%

    No Known Activations