© 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. 12414
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or units

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

    The neuron fires on numeric tokens—any standalone numbers (including dates, section numbers, measurements, etc.).

    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
    日至
    0.91
    到
    0.86
     മുതല്‍
    0.81
    until
    0.81
     تا
    0.80
    年至
    0.80
     থেকে
    0.78
     līdz
    0.77
     到
    0.77
     hingga
    0.75
    POSITIVE LOGITS
     inclusive
    1.21
     inclusiv
    1.09
     Inclusive
    1.03
    inclusive
    0.97
    Inclusive
    0.94
     inclus
    0.87
     вклю
    0.76
     respectivement
    0.76
     jeweils
    0.75
     respectivamente
    0.74
    Activations Density 0.193%

    No Known Activations