© 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. 32829
    Prev
    Next
    INDEX
    Explanations

    hardware/software terms

    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
     Have
    -1.09
    หน้าน
    -0.98
    B
    -0.93
     out
    -0.89
     thinks
    -0.87
    TileEntity
    -0.84
     helps
    -0.82
     Even
    -0.82
    D
    -0.82
     H
    -0.81
    POSITIVE LOGITS
     petits
    1.03
     Retour
    0.98
     Funktionalität
    0.97
     ulo
    0.96
    otras
    0.95
     Merkmale
    0.95
    咂
    0.94
     innate
    0.93
     Rakyat
    0.93
    мѣ
    0.92
    Activations Density 0.051%

    No Known Activations