© 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. 56939
    Prev
    Next
    INDEX
    Explanations

    5 p.m

    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
     in
    -0.81
     Engine
    -0.80
     to
    -0.80
    游戏的
    -0.78
     for
    -0.77
     plainte
    -0.76
    nings
    -0.75
    ℋ
    -0.75
    ueses
    -0.75
     Editor
    -0.74
    POSITIVE LOGITS
     réfrig
    0.97
     мужчи
    0.90
    pædia
    0.87
     Irland
    0.87
     higien
    0.85
     vemos
    0.85
    akha
    0.84
     nomina
    0.83
    űr
    0.83
     descomp
    0.83
    Activations Density 0.555%

    No Known Activations