© 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. 47154
    Prev
    Next
    INDEX
    Explanations

    "Q" or "<?php" or "Abstract" or "6 Precision"

    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
    efd
    -0.86
    rafas
    -0.77
     Standort
    -0.77
     confeder
    -0.72
    Помо
    -0.69
     Dj
    -0.68
     unirse
    -0.68
     никого
    -0.68
    lichung
    -0.68
    Finalmente
    -0.67
    POSITIVE LOGITS
     budgets
    0.79
     yaka
    0.78
    Lav
    0.74
    nye
    0.73
     NATIONAL
    0.73
     ลาย
    0.73
    INSTRUCTIONS
    0.73
     topic
    0.73
    /…
    0.72
    TOPIC
    0.72
    Activations Density 0.023%

    No Known Activations