© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14655
    Prev
    Next
    INDEX
    Explanations

    `waitKey()` or `pledge()`

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

    The neuron is highly sensitive to numeric tokens (including multi-digit numbers, decimals, codes, and identifiers).

    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
     dó
    0.84
    ได้
    0.84
     STS
    0.84
     ม
    0.84
     XR
    0.83
     Vista
    0.82
     sự
    0.82
     NRS
    0.81
     OBD
    0.81
     GSE
    0.81
    POSITIVE LOGITS
    sPath
    0.92
    ों
    0.84
    sini
    0.83
    shen
    0.82
    sock
    0.79
    ре
    0.78
    s
    0.76
    ਆਂ
    0.74
    ের
    0.71
    しており
    0.71
    Activations Density 0.001%

    No Known Activations