© 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. 13625
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens representing floating‐point numbers (i.e. numeric 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
    ی
    0.92
     oficiales
    0.91
     sebuah
    0.83
     सौंपी
    0.82
    ν
    0.81
     productores
    0.81
     capaces
    0.80
     venta
    0.79
     esperar
    0.78
     familias
    0.77
    POSITIVE LOGITS
    ној
    0.79
    করণ
    0.74
    ен
    0.73
    НИ
    0.70
    사의
    0.70
     latest
    0.69
    的所有
    0.69
    ▛
    0.68
    OVERRIDES
    0.67
    ᆷ
    0.67
    Activations Density 0.000%

    No Known Activations