© 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. 33670
    Prev
    Next
    INDEX
    Explanations

    simple

    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
     lustige
    -0.82
    aturi
    -0.81
     mittlere
    -0.78
    씠
    -0.75
    ybės
    -0.75
     vada
    -0.75
    pakah
    -0.74
    othermic
    -0.73
    ceous
    -0.73
    cive
    -0.73
    POSITIVE LOGITS
     simple
    7.97
    simple
    6.72
    Simple
    5.97
     Simple
    5.69
    SIMPLE
    5.34
     simples
    5.28
    简单
    5.19
     semplice
    5.09
     ساده
    4.97
     simplest
    4.94
    Activations Density 0.494%

    No Known Activations