© 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. 24-GEMMASCOPE-2-RES-16K
    7. 613
    Prev
    Next
    INDEX
    Explanations

    The neuron flags standalone numeric tokens—especially multi‐digit decimal 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
     потра
    0.35
    الى
    0.29
    с
    0.29
    0.29
    clid
    0.28
    小数
    0.28
    ğı
    0.28
    不必
    0.28
    同じ
    0.28
    钛
    0.28
    POSITIVE LOGITS
     관련된
    0.34
     Sicherheit
    0.31
     handicrafts
    0.30
     Spirituality
    0.30
    ंगाबाद
    0.29
     Management
    0.29
     management
    0.29
     anderer
    0.28
     sociale
    0.28
     informatics
    0.28
    Activations Density 0.000%

    No Known Activations