© 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. 22-GEMMASCOPE-RES-131K
    7. 64333
    Prev
    Next
    INDEX
    Explanations

    as official, as preceding, as comeback, as GPL

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

    the use of “as” in formal, often passive, status or classification phrases (e.g. “was verified as official,” “were found in,” “were associated as,” etc.)

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     cripto
    -1.13
     them
    -1.02
     sapat
    -1.02
     multa
    -1.02
     illa
    -0.98
     bobina
    -0.96
    :{
    -0.96
     pistola
    -0.94
     bici
    -0.94
    来到
    -0.93
    POSITIVE LOGITS
     posiblemente
    1.19
     of
    1.15
    슷
    1.12
     Angebot
    1.04
     as
    1.03
     ugyan
    1.03
     związku
    1.02
     aparecen
    1.02
     thoáng
    1.02
     aparece
    1.02
    Activations Density 0.000%

    No Known Activations