© 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. 79357
    Prev
    Next
    INDEX
    Explanations

    start of document/section

    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
     emble
    -1.01
     civils
    -0.93
    upyter
    -0.89
    ƨ
    -0.88
     firft
    -0.84
    ുടെ
    -0.83
    原标题
    -0.82
     feveral
    -0.81
     sopp
    -0.79
    rocco
    -0.79
    POSITIVE LOGITS
    砾
    0.88
    той
    0.86
     Thu
    0.83
    tahu
    0.82
    sete
    0.81
    від
    0.81
    Thu
    0.80
     this
    0.79
    masının
    0.79
    руд
    0.77
    Activations Density 0.000%

    No Known Activations