© 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. 34-GEMMASCOPE-RES-131K
    7. 62371
    Prev
    Next
    INDEX
    Explanations

    unicode collation and internationalization

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

    This neuron responds to list-item markers and enumerators—specifically the leading hyphens, numbers, and related tokens that denote bullet points or numbered entries.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     audio
    -0.82
     coast
    -0.78
    thm
    -0.75
    дым
    -0.71
    ップ
    -0.71
    nsyn
    -0.70
    季
    -0.70
     Audio
    -0.70
    ('../../../
    -0.69
     tejidos
    -0.69
    POSITIVE LOGITS
     ICU
    1.07
    ICU
    1.06
     Intl
    0.96
    icu
    0.92
     collation
    0.91
     Unicode
    0.84
     UNIC
    0.82
    collation
    0.82
     Unis
    0.81
     Coll
    0.79
    Activations Density 0.253%

    No Known Activations