© 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. 14715
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens that include decimal points (floating-point numbers).

    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
    >
    0.87
    {
    0.85
    ab
    0.84
    }
    0.81
    amp
    0.80
    ]
    0.79
    a
    0.76
     É
    0.75
    ▪
    0.75
    ل
    0.74
    POSITIVE LOGITS
    бычно
    0.81
     fateful
    0.78
    ಾವಣ
    0.78
     speedboat
    0.78
    перы
    0.77
     এছাড়াও
    0.75
    這裡
    0.75
     উৎসাহিত
    0.74
     आरमार
    0.74
    ट्टर
    0.74
    Activations Density 0.000%

    No Known Activations