© 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. 47344
    Prev
    Next
    INDEX
    Explanations

    source code is governed

    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
     seems
    -0.80
    üchte
    -0.80
    หนัง
    -0.79
     After
    -0.76
     after
    -0.74
    AppBar
    -0.74
    ☀️
    -0.74
     or
    -0.73
     all
    -0.72
     conector
    -0.71
    POSITIVE LOGITS
    ghted
    0.94
    欅
    0.94
     заявил
    0.93
     jaké
    0.91
     rating
    0.90
    连忙
    0.90
    Compati
    0.88
    Spesifikasi
    0.88
     scoring
    0.88
     flair
    0.87
    Activations Density 0.001%

    No Known Activations