© 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. 62489
    Prev
    Next
    INDEX
    Explanations

    DP, TP, RP, VP, LP abbreviations

    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
     knowing
    -0.88
     unless
    -0.84
     why
    -0.82
    terday
    -0.81
    lancer
    -0.78
     obvious
    -0.78
    kuli
    -0.77
    AXB
    -0.75
     schla
    -0.75
    Cfg
    -0.74
    POSITIVE LOGITS
     SINGH
    0.96
    dp
    0.95
     questi
    0.88
    ноза
    0.85
    DEBUG
    0.84
    Những
    0.84
    拣
    0.84
     ра
    0.83
    mp
    0.82
    迸
    0.82
    Activations Density 0.048%

    No Known Activations