© 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. 3781
    Prev
    Next
    INDEX
    Explanations

    competition stages or jurisdictions

    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
    Моя
    -1.40
     about
    -1.40
     avevano
    -1.39
     који
    -1.39
    轱
    -1.37
    有一些
    -1.36
    jelasan
    -1.35
    Anlage
    -1.34
     giusta
    -1.34
    許多
    -1.33
    POSITIVE LOGITS
     ''
    1.68
    ют
    1.42
    媧
    1.39
    ]='\
    1.33
     '
    1.27
    ↵↵
    1.27
    眛
    1.27
     QtCore
    1.26
    ]--;
    1.25
    ilization
    1.24
    Activations Density 0.008%

    No Known Activations