© 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. 16669
    Prev
    Next
    INDEX
    Explanations

    file names and versions

    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
    Varian
    -0.99
    Regi
    -0.98
    Besch
    -0.98
    Memoria
    -0.95
    Rebs
    -0.92
     элемент
    -0.92
     beira
    -0.91
     枚
    -0.91
    Immobili
    -0.90
    Miser
    -0.90
    POSITIVE LOGITS
    Mode
    1.02
     сър
    1.01
     separate
    0.97
    xiii
    0.92
     maupun
    0.91
     separately
    0.85
    Spain
    0.84
     mode
    0.83
    Pane
    0.82
    𝑧
    0.82
    Activations Density 0.005%

    No Known Activations