© 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. 128003
    Prev
    Next
    INDEX
    Explanations

    UI initialization and setup

    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
    Not in Any Lists

    No Comments

    Negative Logits
     pensato
    -1.27
    Sziasztok
    -1.02
     Deixe
    -1.00
     same
    -0.99
    Kedves
    -0.98
     romanzo
    -0.98
    März
    -0.98
     scoperto
    -0.97
    Zubereitung
    -0.96
    TRIBUTION
    -0.96
    POSITIVE LOGITS
     initComponents
    1.11
     startup
    1.10
     establish
    0.96
    ENODEV
    0.96
     시작
    0.96
    了一声
    0.95
    binant
    0.94
    BeginInit
    0.94
    squareup
    0.94
     Inaug
    0.94
    Activations Density 0.003%

    No Known Activations