© 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. 9141
    Prev
    Next
    INDEX
    Explanations

    The neuron spikes on numeric expressions—particularly multi‐digit numbers, times, measurements, or version/decimal values.

    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
    函數
    0.80
     characterize
    0.80
    ↵
    0.79
     emphasize
    0.79
    πο
    0.78
    看護
    0.77
    蔻
    0.77
     be
    0.76
    𝐪
    0.75
    angular
    0.72
    POSITIVE LOGITS
     propias
    0.89
     bliss
    0.88
    "})
    0.87
     vistas
    0.86
     recorr
    0.84
     vidas
    0.83
     себя
    0.81
     hesap
    0.81
     знает
    0.80
     hijas
    0.80
    Activations Density 0.000%

    No Known Activations