© 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. 9816
    Prev
    Next
    INDEX
    Explanations

    contact departments or services

    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
    がなく
    -1.30
    が無い
    -1.23
    不好的
    -1.18
     både
    -1.12
     alcune
    -1.09
     zowel
    -1.08
     ทั้ง
    -1.04
     oberen
    -1.02
     نداشت
    -1.02
     sowohl
    -1.01
    POSITIVE LOGITS
     or
    2.11
     if
    2.05
     at
    1.98
     your
    1.64
     by
    1.43
     in
    1.38
     them
    1.38
     ако
    1.34
     alebo
    1.30
     directly
    1.28
    Activations Density 0.016%

    No Known Activations