© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14144
    Prev
    Next
    INDEX
    Explanations

    archive links and labels

    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
    泐
    -2.89
    埽
    -2.73
    2
    -2.63
    坶
    -2.59
    ྄
    -2.59
    鲞
    -2.52
    骉
    -2.48
    縢
    -2.45
    ඍ
    -2.44
     dà
    -2.42
    POSITIVE LOGITS
     Según
    2.64
    硖
    2.59
    ㌧
    2.56
     After
    2.55
    先は
    2.48
     During
    2.38
     Después
    2.36
     После
    2.36
     Shortly
    2.34
    ᮣ
    2.34
    Activations Density 0.007%

    No Known Activations