© 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. 50222
    Prev
    Next
    INDEX
    Explanations

    plug-in hybrid vehicles

    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
    轮胎
    -0.81
    getAge
    -0.77
    newly
    -0.76
    swim
    -0.74
    zania
    -0.74
    southern
    -0.72
    øya
    -0.72
    hinder
    -0.71
     navegando
    -0.71
    ajuste
    -0.71
    POSITIVE LOGITS
     hybrid
    3.06
    hybrid
    2.28
     Hybrid
    2.23
    Hybrid
    2.20
     hybrids
    2.14
     hybridi
    1.84
     hybride
    1.71
     hybridization
    1.65
     hy
    1.56
    ハイ
    1.31
    Activations Density 0.023%

    No Known Activations