© 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. 2504
    Prev
    Next
    INDEX
    Explanations

    monetary values and prices

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     alve
    0.54
     ০৯
    0.54
     (-
    0.50
     (>
    0.50
     adduct
    0.49
     MEM
    0.49
     JO
    0.48
     (=
    0.48
     glomer
    0.47
    រយៈពេល
    0.47
    POSITIVE LOGITS
     money
    1.50
     денег
    1.49
     деньги
    1.44
     $
    1.41
     dinero
    1.41
     £
    1.38
    money
    1.36
     $\$
    1.33
     dinheiro
    1.33
     dollars
    1.31
    Activations Density 0.453%

    No Known Activations