© 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. 11538
    Prev
    Next
    INDEX
    Explanations

    VINs and identification numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting number tokens and numeric strings (e.g. digits, decimals, quantities).

    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
     эт
    0.52
     তোমাকে
    0.51
    욜
    0.51
    偷
    0.50
    滢
    0.50
    กล่าว
    0.50
    ẍ
    0.50
    枕
    0.49
    🏄
    0.49
    制品
    0.48
    POSITIVE LOGITS
     Parcel
    0.67
     Indoor
    0.65
     indoor
    0.62
     IB
    0.61
     parcel
    0.60
    Plots
    0.60
     plots
    0.59
    屋内
    0.59
     Remote
    0.58
     parcels
    0.58
    Activations Density 0.031%

    No Known Activations