© 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. 13640
    Prev
    Next
    INDEX
    Explanations

    fee or cost

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

    This neuron detects words and phrases related to generating or raising money (e.g., “raising money,” “make big money,” “raise funds”).

    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
     रेपो
    0.60
     deduct
    0.57
    仮
    0.57
    借り
    0.56
     Dedu
    0.55
    freeze
    0.54
     overdraft
    0.53
     dedu
    0.52
     goodwill
    0.52
     commitment
    0.52
    POSITIVE LOGITS
     money
    2.11
     dinero
    2.11
     dinheiro
    2.05
     돈
    2.02
     деньги
    2.00
     profits
    1.98
    money
    1.98
     MONEY
    1.98
     денег
    1.96
    錢
    1.92
    Activations Density 0.640%

    No Known Activations