© 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. 22-GEMMASCOPE-RES-131K
    7. 16550
    Prev
    Next
    INDEX
    Explanations

    www and http beginnings

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     "
    -1.12
    getPrice
    -1.01
     belangrij
    -1.01
     Aseg
    -0.96
    ająca
    -0.96
    ющая
    -0.94
     através
    -0.94
     emberek
    -0.93
    bàn
    -0.93
     '?
    -0.91
    POSITIVE LOGITS
     here
    1.03
     男の子
    0.94
     each
    0.94
     users
    0.93
    either
    0.88
     to
    0.88
    each
    0.85
    morgen
    0.85
    www
    0.85
    TestingModule
    0.85
    Activations Density 0.010%

    No Known Activations