© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66888
    Prev
    Next
    INDEX
    Explanations

    #include directive

    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
     '\\;'
    -1.21
     its
    -1.17
    boldmath
    -1.16
     phía
    -1.06
     וכן
    -1.05
    seamnă
    -1.05
     помочь
    -1.03
     selepas
    -1.03
    angdong
    -1.03
    teinte
    -1.02
    POSITIVE LOGITS
    <>
    1.10
    回想
    1.04
     walang
    1.02
     kani
    1.01
     francês
    0.98
     credito
    0.98
    gallon
    0.97
    шных
    0.96
     lærer
    0.96
     levis
    0.96
    Activations Density 0.021%

    No Known Activations