© 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. 11651
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric values and measurements (tokens containing digits or quantities).

    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
     dico
    0.86
     inizi
    0.83
    珍惜
    0.83
     excret
    0.82
    嗉
    0.81
     स्टूड
    0.81
     Bên
    0.80
    emiz
    0.79
    解答
    0.78
    ぐ
    0.78
    POSITIVE LOGITS
     outliers
    0.77
    НИ
    0.73
     రామ
    0.71
    acks
    0.71
    метри
    0.71
    ват
    0.71
     नका
    0.70
    govt
    0.68
    rossovers
    0.68
    γματα
    0.68
    Activations Density 0.000%

    No Known Activations