© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110861
    Prev
    Next
    INDEX
    Explanations

    internal combustion engines

    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
    無線
    -0.90
    ფ
    -0.84
     viajes
    -0.81
     calidad
    -0.79
    タイヤ
    -0.78
    ágeno
    -0.77
    phene
    -0.77
    icol
    -0.75
    ruecos
    -0.75
     antimicrobial
    -0.75
    POSITIVE LOGITS
     engine
    1.72
     engines
    1.60
     displacement
    1.20
     Engine
    1.18
     emissions
    1.16
     ENGINE
    1.15
     combustion
    1.13
    engine
    1.09
     destro
    1.06
     power
    1.03
    Activations Density 0.064%

    No Known Activations