© 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. 106243
    Prev
    Next
    INDEX
    Explanations

    phase shift

    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
    游
    -0.75
    以前
    -0.74
    Tur
    -0.72
     став
    -0.69
    嶼
    -0.69
    رأ
    -0.69
     Tur
    -0.68
    思
    -0.68
     mercurial
    -0.67
    関
    -0.67
    POSITIVE LOGITS
     phase
    4.16
    phase
    3.48
    Phase
    3.08
     phases
    3.06
     Phase
    3.06
     PHASE
    2.88
    phases
    2.80
     phasing
    2.75
    PHASE
    2.73
    Phases
    2.34
    Activations Density 0.069%

    No Known Activations