© 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. 71590
    Prev
    Next
    INDEX
    Explanations

    there is

    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
     puisque
    -1.09
    んじゃ
    -1.08
     CALIFORN
    -1.03
    べし
    -0.99
     FOUNDATION
    -0.98
     FRANCIS
    -0.98
    Kult
    -0.97
    `.
    -0.96
     HERBERT
    -0.96
    .$$
    -0.95
    POSITIVE LOGITS
     or
    1.17
    liches
    1.02
     keine
    1.00
     consistently
    1.00
     daarna
    0.93
     without
    0.92
     Then
    0.90
     regularly
    0.89
     When
    0.88
     does
    0.87
    Activations Density 0.060%

    No Known Activations