© 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. 47232
    Prev
    Next
    INDEX
    Explanations

    modded APKs Android

    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
    prende
    -0.80
     อาหาร
    -0.77
     Gros
    -0.76
     Programm
    -0.75
    perror
    -0.73
     гостиной
    -0.73
    fton
    -0.73
     Explorer
    -0.73
     eficiencia
    -0.72
    迁
    -0.71
    POSITIVE LOGITS
     MOD
    1.88
     Mod
    1.77
    MOD
    1.74
     mod
    1.67
    Mod
    1.56
     modded
    1.37
    mod
    1.36
     APK
    1.27
    bmod
    1.20
     Apk
    1.14
    Activations Density 0.013%

    No Known Activations