© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14358
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on floating-point numerals (numeric tokens containing digits and a decimal point).

    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
    ति
    0.85
     buts
    0.81
    ات
    0.78
    cies
    0.73
    。
    0.73
    cando
    0.73
    பாத
    0.71
    s
    0.71
    ayers
    0.68
     elles
    0.67
    POSITIVE LOGITS
    망
    0.75
    원의
    0.73
    원은
    0.72
     conduz
    0.71
    )=\
    0.70
    𝔼
    0.70
     informacji
    0.69
     망
    0.69
    MACl
    0.69
    KA
    0.69
    Activations Density 0.000%

    No Known Activations