© 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. 22-GEMMASCOPE-RES-131K
    4. 54539
    Prev
    Next
    INDEX
    Explanations

    comparing to other categories

    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_22/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
    (['/
    -1.05
    anzeige
    -1.05
     marvelous
    -0.98
    fjspx
    -0.96
     puk
    -0.96
    Affirmed
    -0.96
     queste
    -0.95
    さと
    -0.94
    Tensi
    -0.93
     هؤلاء
    -0.92
    POSITIVE LOGITS
     other
    2.78
     других
    1.80
     others
    1.74
     lainnya
    1.73
     similar
    1.66
     otros
    1.62
     innych
    1.61
    อื่น
    1.57
     like
    1.54
     in
    1.52
    Activations Density 0.051%

    No Known Activations