© 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. 34-GEMMASCOPE-RES-131K
    7. 58022
    Prev
    Next
    INDEX
    Explanations

    variable names and Ann Doherty

    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_34/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
    stretchr
    -0.82
     тільки
    -0.80
    үү
    -0.79
    南方
    -0.75
     diser
    -0.73
     naturale
    -0.72
     inneren
    -0.72
    úgó
    -0.71
     ніж
    -0.71
     from
    -0.71
    POSITIVE LOGITS
    变量
    1.13
     Variables
    1.13
    Variables
    1.10
     Variable
    1.05
     variables
    1.05
     variable
    1.04
    variables
    1.03
     перемен
    1.03
    GetType
    1.03
    VARIABLES
    1.00
    Activations Density 0.065%

    No Known Activations