© 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. 106386
    Prev
    Next
    INDEX
    Explanations

    home directory paths

    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
     faculty
    -1.09
    Faculty
    -0.86
     Faculty
    -0.75
    アウト
    -0.71
     lowest
    -0.71
    盤
    -0.70
    abancı
    -0.69
    icitis
    -0.67
    ARG
    -0.67
    vč
    -0.67
    POSITIVE LOGITS
     home
    2.56
    HOME
    2.28
     HOME
    2.09
    home
    2.02
     ~/.
    1.91
    Home
    1.82
     Home
    1.81
     홈
    1.60
     домаш
    1.48
     homes
    1.47
    Activations Density 0.070%

    No Known Activations