© 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. 22-GEMMASCOPE-RES-131K
    7. 95516
    Prev
    Next
    INDEX
    Explanations

    Original Message

    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
     chré
    -1.80
     undervis
    -1.76
    ׇ
    -1.75
     الشاشة
    -1.74
     eccl
    -1.74
     τὸν
    -1.66
     τὰ
    -1.66
     religieuses
    -1.64
     vermel
    -1.58
    Forrás
    -1.56
    POSITIVE LOGITS
    ִּ
    2.41
    ּוֹ
    2.28
     السياس
    2.11
     бампер
    2.09
    ַּ
    1.97
    וּ
    1.68
    ְּ
    1.67
    ֶּ
    1.63
    ָּ
    1.52
     الحكومة
    1.52
    Activations Density 0.006%

    No Known Activations