© 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. 90404
    Prev
    Next
    INDEX
    Explanations

    in phrases

    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
     The
    -1.68
     currently
    -1.56
    ↵↵
    -1.52
    噐
    -1.49
     newer
    -1.48
    a
    -1.48
     вну
    -1.45
    咾
    -1.45
    に行った
    -1.45
     abundant
    -1.43
    POSITIVE LOGITS
     だけ
    1.80
    lorious
    1.74
    since
    1.71
    biendo
    1.70
    は
    1.64
     penyanyi
    1.55
    蓠
    1.53
    Ǻ
    1.52
     では
    1.52
    】：
    1.48
    Activations Density 0.012%

    No Known Activations