© 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. 22-GEMMASCOPE-RES-131K
    7. 70693
    Prev
    Next
    INDEX
    Explanations

    programming commands and syntax

    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_22/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
     anderen
    -1.46
     other
    -1.13
     outros
    -0.98
     auf
    -0.96
     only
    -0.91
     andere
    -0.90
     zich
    -0.90
    rī
    -0.88
     Beruf
    -0.88
    VStack
    -0.87
    POSITIVE LOGITS
    říklad
    1.13
     Minis
    1.08
     Tiga
    0.99
     nắm
    0.98
    phrodite
    0.98
     nướng
    0.98
     Simult
    0.96
     Initialise
    0.95
     productores
    0.94
     growled
    0.94
    Activations Density 0.002%

    No Known Activations