© 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. 56669
    Prev
    Next
    INDEX
    Explanations

    postfach, P.O. Box, or names like Elizabeth, Andrés

    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
     営業
    -1.04
    preso
    -1.00
    平成
    -0.92
     bagno
    -0.90
     mizuno
    -0.90
     combustível
    -0.88
    روب
    -0.85
     losing
    -0.85
     otak
    -0.84
    fatti
    -0.84
    POSITIVE LOGITS
     Box
    1.68
     box
    1.58
    Box
    1.34
     boxes
    1.27
     BOX
    1.25
    box
    1.22
     Boxes
    1.22
     snail
    0.99
    盒子
    0.96
     scams
    0.95
    Activations Density 0.003%

    No Known Activations