© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10875
    Prev
    Next
    INDEX
    Explanations

    selling a business

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

    The neuron strongly fires on the word “associated,” i.e. it detects that exact past‐participle/adjective form.

    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
    ਾਰ
    0.73
    ੯
    0.69
    етки
    0.68
     жүктөө
    0.66
    focusable
    0.65
    몄
    0.64
     రోజుల
    0.63
    megapixel
    0.62
     мүмк
    0.61
    BoxLayout
    0.60
    POSITIVE LOGITS
     validated
    0.68
     چکے
    0.66
     arroz
    0.66
    ना
    0.62
    联合
    0.61
     вже
    0.61
     delicious
    0.60
    まだ
    0.60
     リ
    0.60
    依据
    0.60
    Activations Density 0.000%

    No Known Activations