© 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. 56721
    Prev
    Next
    INDEX
    Explanations

    specifying size

    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
     adds
    -0.98
     survives
    -0.97
     обеспечивает
    -0.96
     chiefly
    -0.94
     derives
    -0.92
    ısından
    -0.91
     revised
    -0.91
    OSPITAL
    -0.90
     Saltar
    -0.90
     maestros
    -0.89
    POSITIVE LOGITS
    icate
    1.20
     CGSize
    1.16
    bigger
    1.12
    UNITIES
    1.12
    zerland
    1.10
     sociala
    1.10
    ᡨ
    1.09
    葑
    1.08
    ।
    1.08
    Smaller
    1.08
    Activations Density 0.046%

    No Known Activations