© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12910
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
     周年
    -1.08
    Most
    -1.02
      (
    -0.91
    Getting
    -0.91
    پرس
    -0.86
    浙江
    -0.86
    湖北
    -0.85
    Both
    -0.85
    During
    -0.83
     belonging
    -0.82
    POSITIVE LOGITS
     instead
    5.44
    instead
    4.19
     вместо
    3.95
     rather
    3.81
    Instead
    3.70
     Instead
    3.47
     zamiast
    3.42
     invece
    3.33
     plutôt
    3.14
    而不是
    3.00
    Activations Density 0.084%

    No Known Activations