© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1253
    Prev
    Next
    INDEX
    Explanations

    The neuron specializes in spotting numerical measurements expressed as decimal (floating‐point) 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_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
    溶液
    0.64
    방법
    0.64
     방법
    0.61
    quée
    0.61
     만큼
    0.60
    兢
    0.60
    用力
    0.59
     방법을
    0.59
    olí
    0.58
    ⌞
    0.58
    POSITIVE LOGITS
     niedr
    0.89
     diameter
    0.88
     characteristics
    0.85
    较高的
    0.85
     высоким
    0.84
     gering
    0.84
     uncertain
    0.83
     faible
    0.83
     hoher
    0.82
     varying
    0.82
    Activations Density 0.641%

    No Known Activations