© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40184
    Prev
    Next
    INDEX
    Explanations

    code main function structure

    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
    tividade
    -1.30
     prêtre
    -1.29
     poussière
    -1.27
     اگر
    -1.26
    ۔
    -1.25
     laatste
    -1.24
    Wichtig
    -1.23
     aptly
    -1.23
    Bibliografía
    -1.23
    訝
    -1.21
    POSITIVE LOGITS
     like
    1.40
     anadolu
    1.19
    Its
    1.15
    /
    1.15
     /
    1.14
     try
    1.14
     passos
    1.13
     hecta
    1.13
     running
    1.10
     issus
    1.05
    Activations Density 0.027%

    No Known Activations