© 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. 65443
    Prev
    Next
    INDEX
    Explanations

    home theaters or gardens

    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
    sqcup
    -1.43
     in
    -1.42
     важно
    -1.35
    1
    -1.35
     міста
    -1.35
     проє
    -1.31
     because
    -1.31
     дії
    -1.29
     एवं
    -1.26
     області
    -1.25
    POSITIVE LOGITS
     rente
    1.59
    奩
    1.44
    喁
    1.43
    粜
    1.38
     minera
    1.37
    幛
    1.36
     tels
    1.33
    蹀
    1.29
     сумка
    1.28
     книг
    1.25
    Activations Density 0.110%

    No Known Activations