© 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. 127872
    Prev
    Next
    INDEX
    Explanations

    programming language file extensions

    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
    at
    -1.20
     møte
    -1.13
     而
    -1.01
    出了一
    -0.99
    but
    -0.98
    in
    -0.97
     besök
    -0.97
     lakini
    -0.94
    é
    -0.93
    而
    -0.93
    POSITIVE LOGITS
     آنچه
    0.98
    ゚
    0.94
    expectation
    0.93
     bestellt
    0.93
     moléculas
    0.93
     appelez
    0.92
     verzichten
    0.90
    expectations
    0.90
     schien
    0.89
    Bridget
    0.89
    Activations Density 0.004%

    No Known Activations