© 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. 6437
    Prev
    Next
    INDEX
    Explanations

    The neuron specifically lights up on decimal-formatted numeric tokens (i.e. 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_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
    𝕥
    0.83
    𝓎
    0.81
     fallo
    0.80
    éal
    0.79
    郸
    0.79
    ون
    0.79
     outage
    0.78
     deutlich
    0.77
    延迟
    0.77
    直
    0.77
    POSITIVE LOGITS
     Гра
    0.77
     Люди
    0.71
     Эти
    0.70
     Neg
    0.68
     نگر
    0.68
     الانسان
    0.67
     воздей
    0.66
     dehuman
    0.66
     власть
    0.64
     Feminist
    0.64
    Activations Density 0.000%

    No Known Activations