© 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. 110907
    Prev
    Next
    INDEX
    Explanations

    kotlin keywords: val, fun

    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
    ()]
    
    -0.97
    Nous
    -0.92
    цію
    -0.91
     السيارة
    -0.87
    inders
    -0.86
    يت
    -0.86
     ascii
    -0.85
    []{"
    -0.85
    Crossref
    -0.85
    creat
    -0.84
    POSITIVE LOGITS
     fun
    2.00
    fun
    1.77
     FUN
    1.32
     Fun
    1.21
    val
    1.07
    Fun
    1.02
     divertido
    0.96
    FUN
    0.95
     val
    0.87
     also
    0.78
    Activations Density 0.004%

    No Known Activations