© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15792
    Prev
    Next
    INDEX
    Explanations

    inflation data CPI index

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

    The neuron strongly activates on numeric data tokens—especially decimal‐formatted values and economic/statistical indices (e.g. CPI figures).

    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
     сре
    0.69
     lao
    0.59
     pec
    0.57
    Tokenizer
    0.57
    珍惜
    0.56
    )/(
    0.55
     витра
    0.55
     souhaitez
    0.53
     Ruskin
    0.53
    所以在
    0.53
    POSITIVE LOGITS
     اعلی
    0.63
    ডিয়াম
    0.62
     superb
    0.61
     Resmi
    0.61
    勮
    0.61
     Сі
    0.57
    endpoints
    0.57
    និង
    0.57
    agré
    0.57
    endpoint
    0.56
    Activations Density 0.000%

    No Known Activations