© 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. 62527
    Prev
    Next
    INDEX
    Explanations

    programming and code syntax

    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
    週末
    -0.89
     accesible
    -0.80
     Allegheny
    -0.75
    据说
    -0.75
     khán
    -0.73
    Groot
    -0.73
    řad
    -0.73
     sobri
    -0.72
    rax
    -0.72
    zerne
    -0.71
    POSITIVE LOGITS
     Alabama
    1.92
    Alabama
    1.66
     Birmingham
    1.38
    Birmingham
    1.16
     ARM
    1.05
     Mobile
    1.04
     UAB
    1.01
     Auburn
    0.94
     Thumb
    0.93
     Huntsville
    0.93
    Activations Density 0.007%

    No Known Activations