© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32298
    Prev
    Next
    INDEX
    Explanations

    lemon and lemonade

    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
     superposition
    -0.84
    aes
    -0.82
    調整
    -0.79
     refirió
    -0.78
     navideño
    -0.77
     sepol
    -0.76
     lv
    -0.76
    いに
    -0.75
     delineated
    -0.75
     verurs
    -0.74
    POSITIVE LOGITS
    🍋
    1.50
     balm
    0.99
     zest
    0.96
     meringue
    0.92
    ades
    0.89
     groves
    0.87
     Lem
    0.86
     yellow
    0.86
    яти
    0.84
     Grove
    0.84
    Activations Density 0.004%

    No Known Activations