© 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. 6228
    Prev
    Next
    INDEX
    Explanations

    purchasing power of money

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

    The neuron strongly activates on multi‐digit numeric tokens—i.e. large numbers rather than words.

    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
     inflación
    0.70
     inflation
    0.63
     Inflation
    0.61
     Adjusted
    0.60
     transgender
    0.57
     adjusting
    0.56
     adjusts
    0.56
    広
    0.55
     Adjust
    0.54
    Adjust
    0.54
    POSITIVE LOGITS
     отве
    0.62
     Phenomen
    0.55
     saque
    0.55
     конструкция
    0.54
    ','"
    0.54
    ാരണ
    0.53
     shawl
    0.53
     রকমের
    0.53
    aphthal
    0.53
     tunique
    0.53
    Activations Density 0.000%

    No Known Activations