© 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. 129834
    Prev
    Next
    INDEX
    Explanations

    foreign and specialized terms

    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
    лко
    -1.01
     niệm
    -0.81
     lurking
    -0.79
    observation
    -0.78
     gymnastics
    -0.76
     fashionable
    -0.76
    }:{
    -0.76
    孝
    -0.73
    обе
    -0.73
     tucked
    -0.73
    POSITIVE LOGITS
     juist
    1.20
     דו
    1.02
    ghis
    1.01
     unab
    0.96
    どのような
    0.92
    gub
    0.90
    あえて
    0.90
    BOLD
    0.86
     наоборот
    0.84
    challenge
    0.84
    Activations Density 0.047%

    No Known Activations