© 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. 15194
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on long numerical tokens—especially multi‐digit numbers with decimal points (e.g. large floating-point 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
    *=
    0.64
     Irrigation
    0.60
     Preheat
    0.60
    *
    0.60
     WebDriver
    0.59
     فقد
    0.58
     гран
    0.58
     tartoz
    0.58
    مة
    0.58
    ्स
    0.57
    POSITIVE LOGITS
    destruction
    0.84
    ar
    0.82
    ことにより
    0.80
    financing
    0.79
    িক
    0.79
    盎
    0.79
    okk
    0.78
     distributions
    0.78
     ventures
    0.78
    කො
    0.77
    Activations Density 0.000%

    No Known Activations