© 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. 6691
    Prev
    Next
    INDEX
    Explanations

    The neuron detects the decimal‐formatted time or metadata values (the floating-point numbers) in post headers.

    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
     Außerdem
    0.91
    ﻁ
    0.84
     Поскольку
    0.80
    陴
    0.80
     Кроме
    0.79
     Эти
    0.78
     DISCLAIMED
    0.78
     переза
    0.77
     hemolytic
    0.77
     URANIUM
    0.75
    POSITIVE LOGITS
    L
    0.95
    ↵
    0.90
    times
    0.88
    time
    0.87
     duração
    0.86
     iniziale
    0.86
     iniziare
    0.86
    suits
    0.85
    ي
    0.84
    сті
    0.82
    Activations Density 0.000%

    No Known Activations