© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4467
    Prev
    Next
    INDEX
    Explanations

    next word or item

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

    This neuron detects numeric tokens (quantities, years, or other numbers), especially those with decimal points.

    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
    нің
    1.13
     essentiellement
    0.93
     изначально
    0.89
     实现
    0.89
     oxidase
    0.85
     medallist
    0.84
    珅
    0.84
    ну
    0.83
     celulares
    0.83
    இந்த
    0.80
    POSITIVE LOGITS
    are
    1.11
    ます
    1.01
     few
    0.96
    ടുത്ത
    0.92
    few
    0.91
    sing
    0.89
    どう
    0.88
     próximas
    0.86
    est
    0.86
     paio
    0.84
    Activations Density 0.077%

    No Known Activations