© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94022
    Prev
    Next
    INDEX
    Explanations

    julia code or documentation

    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
     python
    -0.74
    rictions
    -0.73
     Durand
    -0.72
    digheid
    -0.71
     dia
    -0.70
     deceiving
    -0.69
     Dia
    -0.68
     longs
    -0.68
    SALUD
    -0.66
     כא
    -0.66
    POSITIVE LOGITS
    println
    1.15
     println
    1.09
    >:
    0.91
    jl
    0.87
    (::
    0.86
    宏
    0.85
    elseif
    0.85
    nothing
    0.83
    JL
    0.78
    julia
    0.77
    Activations Density 0.026%

    No Known Activations