© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47822
    Prev
    Next
    INDEX
    Explanations

    version specifiers

    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
    ↵↵↵
    -2.11
    珖
    -1.96
     zostały
    -1.95
    "]
    -1.88
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.80
     about
    -1.80
    梱
    -1.78
    ","
    -1.77
    ⼥
    -1.77
    ，，
    -1.75
    POSITIVE LOGITS
    TemporalType
    2.33
    ’
    2.14
    咿
    2.06
    licante
    2.05
    ueltos
    2.05
     faſt
    2.00
    versiti
    1.93
     detest
    1.91
    冬の
    1.88
    oluene
    1.87
    Activations Density 0.041%

    No Known Activations