© 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. 119964
    Prev
    Next
    INDEX
    Explanations

    conditional requests or advice

    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
    全体的に
    -1.38
     servem
    -1.35
     adaptarse
    -1.33
     funcionam
    -1.30
    違います
    -1.27
     terão
    -1.23
    異なります
    -1.23
     ajudam
    -1.20
     compreender
    -1.20
     distinguir
    -1.20
    POSITIVE LOGITS
     if
    1.88
     it
    1.53
    '";
    1.50
    "}";
    1.47
     while
    1.45
     using
    1.45
     with
    1.43
     și
    1.42
     воспользова
    1.38
     några
    1.37
    Activations Density 0.175%

    No Known Activations