© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7255
    Prev
    Next
    INDEX
    Explanations

    The neuron flags numeric monetary amounts (e.g. grants, funding figures, costs) 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
     shampoos
    0.64
     dailySales
    0.56
     ভেসে
    0.56
     ভর্তি
    0.55
     bullion
    0.55
    卖
    0.55
     vaulted
    0.54
     shampoo
    0.54
    賣
    0.54
     tuck
    0.53
    POSITIVE LOGITS
     grant
    2.38
     grants
    2.28
    grant
    2.16
     Grants
    2.11
     Grant
    2.03
    Grant
    2.02
     GRANT
    1.88
     funding
    1.86
     grantees
    1.82
     Funding
    1.76
    Activations Density 0.405%

    No Known Activations