© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6618
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical or digit‐based tokens (e.g. statistics, measurements, or figures) 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_24_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
    ↵↵
    0.84
    4
    0.81
    0
    0.80
     J
    0.76
     T
    0.75
    2
    0.74
    J
    0.74
    0.73
    3
    0.72
     K
    0.70
    POSITIVE LOGITS
     вследствие
    0.70
     permasalahan
    0.69
     различных
    0.66
    DanhMucSP
    0.66
     materialistic
    0.66
     पश्चात
    0.66
    desPort
    0.66
     تمامی
    0.65
    謁
    0.64
    が存在
    0.64
    Activations Density 1.114%

    No Known Activations