© 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. 22-GEMMASCOPE-RES-131K
    7. 79893
    Prev
    Next
    INDEX
    Explanations

    multilingual totals and subtotals

    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
     after
    -1.13
    Both
    -1.09
     information
    -1.05
    ༷
    -1.04
    Although
    -1.02
     équip
    -1.02
     following
    -1.00
    After
    -1.00
     wusste
    -0.99
    However
    -0.98
    POSITIVE LOGITS
     अन्य
    1.44
    Subtotal
    1.40
    อื่น
    1.40
     other
    1.31
    その他
    1.24
     otros
    1.24
     insgesamt
    1.24
     total
    1.23
     سایر
    1.22
     innych
    1.12
    Activations Density 0.006%

    No Known Activations