© 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. 19093
    Prev
    Next
    INDEX
    Explanations

    coal

    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
    ’
    -2.78
     него
    -2.36
    d
    -2.34
    跺
    -2.34
     spooky
    -2.33
    所能
    -2.31
    en
    -2.31
     tens
    -2.30
     年代
    -2.28
    ING
    -2.27
    POSITIVE LOGITS
    釭
    3.14
     剧照
    2.52
     adesivos
    2.50
     órgano
    2.47
    卝
    2.39
    橚
    2.39
     respective
    2.38
     pavimento
    2.31
    ſten
    2.30
    镚
    2.30
    Activations Density 0.002%

    No Known Activations