© 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. 34-GEMMASCOPE-RES-131K
    4. 33142
    Prev
    Next
    INDEX
    Explanations

    code snippets or structured text

    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_34/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
     while
    -0.98
     because
    -0.97
     despite
    -0.94
     before
    -0.94
     so
    -0.94
     many
    -0.91
     for
    -0.90
     sizeable
    -0.88
     several
    -0.88
     after
    -0.87
    POSITIVE LOGITS
     wonderfully
    1.11
     ざ
    0.98
     delightfully
    0.98
     idiotic
    0.97
     astonishing
    0.96
     jednej
    0.95
     startling
    0.93
    nade
    0.93
     marvelous
    0.93
     joyful
    0.92
    Activations Density 0.001%

    No Known Activations