© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6280
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on decimal numbers (floating‐point numeric values) in the text.

    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_31_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
     waveguides
    0.81
    писание
    0.79
    бина
    0.77
    芪
    0.77
    ปี
    0.74
    катери
    0.73
     памяти
    0.73
    Хо
    0.73
     rewire
    0.73
    Ги
    0.72
    POSITIVE LOGITS
    en
    0.66
    PA
    0.66
    expl
    0.66
    omm
    0.64
    lasso
    0.64
    onne
    0.63
    pto
    0.62
    uj
    0.61
    ],
    0.60
     Pull
    0.60
    Activations Density 0.000%

    No Known Activations