© 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. 34-GEMMASCOPE-RES-131K
    7. 91370
    Prev
    Next
    INDEX
    Explanations

    principle of operation

    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_34/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
    OrderID
    -0.90
     identité
    -0.89
     quatrième
    -0.87
    になったら
    -0.84
     verir
    -0.82
     bijvoorbeeld
    -0.81
     jednej
    -0.81
    tacle
    -0.79
     drugi
    -0.79
    ternos
    -0.78
    POSITIVE LOGITS
     principle
    3.92
     principles
    3.30
    原理
    3.13
    principle
    2.84
    Principle
    2.78
     Principle
    2.75
     принцип
    2.61
     mechanism
    2.56
    нцип
    2.45
     принци
    2.39
    Activations Density 0.188%

    No Known Activations