© 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. 32618
    Prev
    Next
    INDEX
    Explanations

    bowl games and food bowls

    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
    らく
    -0.98
    responseBody
    -0.87
     條
    -0.82
    ۱۱
    -0.82
     líquido
    -0.81
     $\%$
    -0.81
     cercanas
    -0.80
     öffnet
    -0.80
    municipi
    -0.79
    无比
    -0.78
    POSITIVE LOGITS
     bowl
    1.45
     Bowl
    1.43
    bowl
    1.31
    Bowl
    1.13
     bowls
    1.06
    bow
    0.97
    Bow
    0.96
     Bow
    0.94
    🎳
    0.93
    </strong>
    0.88
    Activations Density 0.013%

    No Known Activations