© 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. 16745
    Prev
    Next
    INDEX
    Explanations

    functions and properties

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Că
    -0.94
     اپنے
    -0.93
     çünkü
    -0.93
     communiqué
    -0.92
     communique
    -0.84
    헝
    -0.83
     قوات
    -0.82
    Calib
    -0.81
    Azi
    -0.80
    Grup
    -0.80
    POSITIVE LOGITS
     sowohl
    1.12
    Acest
    1.09
     Características
    1.05
    illante
    1.05
     recomendable
    1.05
     تضيف
    1.02
     температуре
    1.02
     anvä
    1.01
    pagnole
    0.97
     funzioni
    0.96
    Activations Density 0.111%

    No Known Activations