© 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. 104766
    Prev
    Next
    INDEX
    Explanations

    car parts and panels

    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
     therefore
    -1.22
     only
    -1.16
     expansive
    -1.16
     this
    -1.14
     any
    -1.12
     quindi
    -1.10
    řízen
    -1.09
    且
    -1.06
    使用
    -1.05
     truly
    -1.05
    POSITIVE LOGITS
     .........
    1.66
     ...........
    1.56
     .......
    1.55
     ..........
    1.51
     ........
    1.48
     .............
    1.41
    絎
    1.36
     ............
    1.30
     ..............
    1.30
     !!!!!
    1.27
    Activations Density 0.049%

    No Known Activations