© 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. 105315
    Prev
    Next
    INDEX
    Explanations

    words followed by specific words

    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
    ﮭ
    -1.35
     kolye
    -1.34
    several
    -1.28
     elbise
    -1.28
    Such
    -1.27
    ˍ
    -1.24
     kaplama
    -1.23
    
    -1.23
     furnishings
    -1.23
     azione
    -1.23
    POSITIVE LOGITS
    </td>
    1.36
    ></
    1.31
     использовать
    1.30
    ارج
    1.27
    剮
    1.25
    玉米
    1.24
     up
    1.23
    ьере
    1.23
    poptotic
    1.20
    ربع
    1.17
    Activations Density 0.237%

    No Known Activations