© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102115
    Prev
    Next
    INDEX
    Explanations

    align left or justify

    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
     -
    -2.08
     They
    -1.99
     Gesetze
    -1.95
     So
    -1.89
    р
    -1.88
     Another
    -1.82
     Simply
    -1.77
     durante
    -1.77
     Similarly
    -1.72
     Zuhause
    -1.72
    POSITIVE LOGITS
     beslu
    1.91
    オ
    1.84
     ourselves
    1.83
     hjelp
    1.78
     fråga
    1.76
    瀏
    1.75
    8
    1.75
    孓
    1.74
    コ
    1.73
    You
    1.70
    Activations Density 0.003%

    No Known Activations