© 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. 56652
    Prev
    Next
    INDEX
    Explanations

    expressions followed by questions

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Known
    -0.92
     პ
    -0.85
     Trọng
    -0.84
     which
    -0.83
    слет
    -0.81
     bună
    -0.81
    Sự
    -0.80
    ngOn
    -0.79
     rehabilitación
    -0.78
    значно
    -0.78
    POSITIVE LOGITS
     klasik
    1.00
     deklar
    0.95
     svin
    0.91
     kust
    0.84
     metodi
    0.83
     lju
    0.83
    حوال
    0.82
     élève
    0.79
    瓛
    0.79
    Seguridad
    0.78
    Activations Density 0.002%

    No Known Activations