© 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. 9489
    Prev
    Next
    INDEX
    Explanations

    You Need a Budget

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

    The neuron fires on numeric tokens—especially multi‐digit and decimal numbers—i.e. explicit quantitative values 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
     criticized
    0.54
    If
    0.52
    II
    0.52
    힘
    0.52
    పాద
    0.51
     Rape
    0.51
     questioned
    0.50
    ős
    0.50
     lupus
    0.49
    ulkar
    0.49
    POSITIVE LOGITS
    駅
    0.57
    坑
    0.56
    খ্যান
    0.55
     ángulos
    0.55
     Hola
    0.55
     駅
    0.54
    Ꮎ
    0.54
    iejs
    0.54
    駅から
    0.54
    ractor
    0.53
    Activations Density 0.049%

    No Known Activations