© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to content-bearing words (nouns and verbs) rather than function words or punctuation.

    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
     (
    0.84
    —
    0.81
    ,
    0.76
    0.73
     ′
    0.70
     …
    0.70
     \(
    0.68
     ʼ
    0.68
     ð
    0.67
    <0xE2>
    0.66
    POSITIVE LOGITS
    ॔
    1.33
    的的
    1.15
     পরিমান
    1.07
     पीछ
    1.02
    둰
    1.02
    lly
    1.02
    mming
    1.01
     부터
    1.00
     तैया
    0.98
    postion
    0.98
    Activations Density 1.036%

    No Known Activations