© 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. 66693
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence connectors

    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
    針對
    -1.09
     obrázok
    -0.95
    established
    -0.92
    utilized
    -0.90
    upported
    -0.89
    primarily
    -0.87
    bulin
    -0.87
     powiedział
    -0.84
    brates
    -0.84
     places
    -0.83
    POSITIVE LOGITS
     using
    1.28
     tragé
    1.11
    يج
    0.96
    Gön
    0.93
     donde
    0.93
     requiring
    0.92
     whose
    0.91
     cuya
    0.90
     dimana
    0.90
    坚定
    0.90
    Activations Density 0.182%

    No Known Activations