© 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. 59829
    Prev
    Next
    INDEX
    Explanations

    enterprises and company activities

    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
    '
    -3.44
    絎
    -2.83
    2
    -2.72
    甞
    -2.72
    despite
    -2.55
     decidedly
    -2.52
     ſaid
    -2.47
     juſt
    -2.42
    鬭
    -2.33
    ピアス
    -2.31
    POSITIVE LOGITS
    訛
    2.53
     exquisite
    2.45
     люди
    2.34
     Both
    2.34
     TWO
    2.34
    谖
    2.27
     dazzling
    2.27
    amoan
    2.25
                    
    2.23
    籐
    2.23
    Activations Density 0.008%

    No Known Activations