© 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. 75013
    Prev
    Next
    INDEX
    Explanations

    punctuation and markup characters

    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
    </h3>
    -1.59
     enhances
    -1.42
    </h6>
    -1.39
     ”
    -1.38
     enhancing
    -1.28
     suggests
    -1.26
    贋
    -1.23
     providing
    -1.21
     dazzling
    -1.20
    ?”
    -1.20
    POSITIVE LOGITS
     eğer
    1.46
    
    1.40
    ’
    1.37
     ſever
    1.32
    尤其
    1.32
     หลัง
    1.31
    是怎么回事
    1.30
    
    1.30
    事も
    1.28
     маленьких
    1.28
    Activations Density 0.001%

    No Known Activations