© 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. 41546
    Prev
    Next
    INDEX
    Explanations

    long data type

    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
    0
    -3.73
     
    -3.61
    ↵↵
    -3.36
      
    -3.30
    Although
    -2.95
    This
    -2.95
    There
    -2.86
    1
    -2.86
    *
    -2.78
    -
    -2.77
    POSITIVE LOGITS
    s
    5.38
    黉
    3.16
    Ꮓ
    3.03
    埽
    2.97
    饪
    2.97
    釤
    2.89
    𓋼
    2.86
    termilk
    2.84
    ی
    2.83
    赑
    2.83
    Activations Density 0.008%

    No Known Activations