© 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. 66684
    Prev
    Next
    INDEX
    Explanations

    sentence starts after punctuation

    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
     using
    -1.63
     use
    -1.52
     used
    -1.46
     uses
    -1.38
     medical
    -1.34
     large
    -1.30
     many
    -1.29
     three
    -1.27
     technology
    -1.27
     data
    -1.27
    POSITIVE LOGITS
     comentário
    1.60
     abraço
    1.45
    皷
    1.41
    回到了
    1.31
     gefe
    1.26
     heilig
    1.23
     intelig
    1.21
     ハーフ
    1.20
     derni
    1.20
     kinda
    1.20
    Activations Density 0.204%

    No Known Activations