© 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. 12391
    Prev
    Next
    INDEX
    Explanations

    interest rate formulas

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

    The main thing this neuron does is detect floating-point numbers (numeric tokens containing a decimal point).

    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
    簡
    0.60
    歡
    0.56
     Version
    0.55
    ﺒ
    0.55
    帮助
    0.55
     เวอร์ชั่น
    0.55
     แ
    0.54
    欢乐
    0.54
    幫助
    0.53
     Fateh
    0.52
    POSITIVE LOGITS
    indic
    0.61
    itm
    0.59
    ............
    0.57
    ...........
    0.56
     ያስፈል
    0.56
    Benzyloxy
    0.56
    pyr
    0.55
     rossa
    0.55
    ították
    0.55
     ಔಷ
    0.55
    Activations Density 0.000%

    No Known Activations