© 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. 377
    Prev
    Next
    INDEX
    Explanations

    New express bus route

    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
     ۱۶
    -1.31
     ۱۸
    -1.23
     Inoltre
    -1.19
     ۱۷
    -1.19
     ۱۲
    -1.18
    felizmente
    -1.17
     They
    -1.14
    arthed
    -1.11
     ۱۵
    -1.10
    <bos>
    -1.09
    POSITIVE LOGITS
     if
    1.37
     its
    1.35
     either
    1.26
    🪙
    1.19
     it
    1.15
     has
    1.14
     had
    1.09
     his
    1.08
    当前
    1.07
    ]++;
    1.05
    Activations Density 0.006%

    No Known Activations