© 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. 75393
    Prev
    Next
    INDEX
    Explanations

    punctuation and discourse markers

    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
     フル
    -0.94
    不太
    -0.93
    TRADE
    -0.93
     caution
    -0.93
    ໊
    -0.92
    atrices
    -0.91
    とはいえ
    -0.91
     favore
    -0.89
    ско
    -0.89
    可惜
    -0.89
    POSITIVE LOGITS
     it
    1.13
     people
    1.02
     what
    1.02
    團隊
    0.96
     Numerous
    0.91
     Often
    0.91
    Often
    0.91
     want
    0.90
     different
    0.90
     went
    0.90
    Activations Density 0.075%

    No Known Activations