© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45660
    Prev
    Next
    INDEX
    Explanations

    Sharia, Malaria, Araucaria

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

    The neuron detects the word "aria" and similar linguistic patterns in various contexts, including technical, scientific, and legal terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron fires on tokens containing the character sequence “aria,” i.e. words ending or including “aria.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ing
    -2.69
    ).
    -2.59
     officielles
    -2.56
     contemporaine
    -2.52
    了
    -2.42
    It
    -2.41
     privées
    -2.41
    ꦴ
    -2.39
    E
    -2.39
     или
    -2.38
    POSITIVE LOGITS
    aria
    3.31
    ARIA
    2.89
     are
    2.50
    锷
    2.48
     the
    2.38
    我只
    2.36
     voltak
    2.30
     excell
    2.27
     pertence
    2.27
     colocando
    2.25
    Activations Density 0.007%

    No Known Activations