© 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. 30263
    Prev
    Next
    INDEX
    Explanations

    in followed by description

    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
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -1.10
    这个
    -1.06
     amount
    -0.91
    anyahu
    -0.88
    这里
    -0.85
    力
    -0.85
    cological
    -0.82
    一个
    -0.81
    任何
    -0.81
    地
    -0.81
    POSITIVE LOGITS
     triplicate
    1.32
     miniature
    1.32
     jugé
    1.13
     italics
    1.05
    ɶ
    1.00
     sereia
    0.97
     excruciating
    0.96
    miniature
    0.94
     glorious
    0.93
     pixels
    0.92
    Activations Density 0.114%

    No Known Activations