© 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. 94077
    Prev
    Next
    INDEX
    Explanations

    programming and technical 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    megen
    -0.93
     verschiedenen
    -0.87
    tamia
    -0.84
    medlem
    -0.82
    страницу
    -0.82
    乾隆
    -0.82
    Чтоб
    -0.81
     may
    -0.80
    Puede
    -0.80
     folgenden
    -0.79
    POSITIVE LOGITS
     και
    1.03
     behov
    1.01
    ープル
    1.00
     Moon
    0.97
     systém
    0.96
     Little
    0.95
     époux
    0.93
    !")
    0.93
    raisers
    0.92
     tourisme
    0.91
    Activations Density 0.073%

    No Known Activations