© 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. 127835
    Prev
    Next
    INDEX
    Explanations

    additional fees and shipping

    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
    ệm
    -1.04
     also
    -0.94
     teorías
    -0.91
     כך
    -0.91
     Zwecke
    -0.90
    IMES
    -0.89
     поддержки
    -0.88
     acidente
    -0.88
     сегодняш
    -0.88
    تاريخ
    -0.87
    POSITIVE LOGITS
     if
    1.27
     any
    1.27
     nor
    1.10
     additional
    1.05
    któ
    1.03
     unless
    1.02
     outside
    0.99
    外
    0.99
     but
    0.91
     jika
    0.91
    Activations Density 0.009%

    No Known Activations