© 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. 106355
    Prev
    Next
    INDEX
    Explanations

    border security and control

    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
     vôtre
    -1.06
     решил
    -0.96
     République
    -0.88
    theres
    -0.85
     большие
    -0.84
    ВЫ
    -0.84
    ඞ
    -0.83
     Révolution
    -0.82
     armada
    -0.82
    ブレム
    -0.81
    POSITIVE LOGITS
    less
    1.36
     crossing
    1.31
     collie
    1.26
    鐢
    1.13
     между
    1.08
     crossings
    1.06
     patrol
    1.05
    lands
    1.00
    laise
    0.99
     Crossing
    0.97
    Activations Density 0.010%

    No Known Activations