© 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. 10-GEMMASCOPE-RES-131K
    7. 70502
    Prev
    Next
    INDEX
    Explanations

    words ending in suffix

    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_10/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
    {
    -2.61
    鹮
    -2.58
    ,’’
    -2.25
    }}\
    -2.23
    ܊
    -2.22
    
    -2.20
    ")){
    -2.20
    潢
    -2.17
    />
    -2.14
     wła
    -2.11
    POSITIVE LOGITS
    s
    3.58
    h
    2.47
    ities
    2.45
    言えば
    2.41
    3
    2.41
     &
    2.38
    ↵
    2.36
     '
    2.30
    <bos>
    2.17
    4
    2.17
    Activations Density 0.003%

    No Known Activations