© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59128
    Prev
    Next
    INDEX
    Explanations

    stories about people and places

    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
    fristi
    -1.02
    athed
    -0.98
     republiky
    -0.93
     Sneakers
    -0.91
    umers
    -0.88
     PROJECTS
    -0.87
     dalších
    -0.86
     다시
    -0.85
    Cursors
    -0.84
    documented
    -0.84
    POSITIVE LOGITS
    During
    1.13
    Once
    1.05
     wealthy
    1.04
     During
    1.00
    There
    0.99
    After
    0.98
    有一天
    0.96
     asked
    0.92
     Once
    0.90
     visited
    0.86
    Activations Density 0.038%

    No Known Activations