© 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. 5087
    Prev
    Next
    INDEX
    Explanations

    The neuron fires specifically on occurrences of the word “Star.”

    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
     MDET
    0.67
     persistent
    0.65
     Jacques
    0.63
    仯
    0.63
     secondes
    0.63
     gauss
    0.63
     segundos
    0.62
     Paddington
    0.62
     otot
    0.62
     Gauss
    0.62
    POSITIVE LOGITS
     星
    1.34
     звез
    1.21
    星
    1.16
     스타
    1.13
    Star
    1.13
    STAR
    1.11
     Stars
    1.09
     star
    1.09
     Star
    1.08
     stars
    1.04
    Activations Density 0.186%

    No Known Activations