© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3449
    Prev
    Next
    INDEX
    Explanations

    The neuron mainly fires on numeric tokens and numeric expressions (e.g. dates, quantities, prices, measurements).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    着的
    0.47
    ټر
    0.39
    intendent
    0.38
    astava
    0.36
    ifiers
    0.36
     없
    0.35
    FileUtils
    0.35
    誑
    0.35
    reflectionCamera
    0.34
    ുകൊണ്ട
    0.34
    POSITIVE LOGITS
    ¨
    0.36
     Fr
    0.35
     añadido
    0.33
     sd
    0.32
     scissor
    0.31
    [][]
    0.31
     mellitus
    0.31
     абсолютно
    0.31
    <0xE3>
    0.30
     diast
    0.30
    Activations Density 0.083%

    No Known Activations