© 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. 23499
    Prev
    Next
    INDEX
    Explanations

    Toyota Mega Cruiser

    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
    匕
    -0.76
     pengh
    -0.73
    motherapy
    -0.72
     most
    -0.69
     kereta
    -0.68
     libras
    -0.68
    oki
    -0.68
     especies
    -0.67
     през
    -0.66
     ré
    -0.66
    POSITIVE LOGITS
     Cruiser
    1.15
     FJ
    1.09
     Land
    1.09
     cruisers
    1.03
     cruiser
    1.00
     Prado
    0.98
    Amazon
    0.94
    cruiser
    0.89
     land
    0.88
     LC
    0.88
    Activations Density 0.015%

    No Known Activations