© 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. 22767
    Prev
    Next
    INDEX
    Explanations

    young ages and age groups

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    We
    -1.47
     of
    -1.46
    TacToe
    -1.43
     sayur
    -1.40
     régi
    -1.35
     beschränkt
    -1.31
    quelles
    -1.31
     ſome
    -1.30
     finalmente
    -1.29
    });
    -1.28
    POSITIVE LOGITS
     Перейти
    1.65
     who
    1.52
    濰
    1.50
     sencillas
    1.49
     světa
    1.48
    izawa
    1.46
    锘
    1.45
     optar
    1.43
    ărat
    1.41
    翾
    1.41
    Activations Density 0.047%

    No Known Activations