© 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. 10-GEMMASCOPE-RES-131K
    4. 65590
    Prev
    Next
    INDEX
    Explanations

    question starters and related nouns

    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_10/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
    3
    -1.67
    >
    -1.58
    ><
    -1.55
     Those
    -1.55
    There
    -1.52
     This
    -1.52
    ки
    -1.51
     However
    -1.48
    <
    -1.48
     Remember
    -1.47
    POSITIVE LOGITS
     kado
    1.52
    wakili
    1.49
    🤣🤣🤣
    1.45
     münchen
    1.45
     oock
    1.45
    🤚
    1.45
     gewi
    1.41
     boks
    1.38
     kedai
    1.38
     bluse
    1.36
    Activations Density 0.006%

    No Known Activations