© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1478
    Prev
    Next
    INDEX
    Explanations

    eggs and Jesus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     अनुबंध
    0.44
     kN
    0.44
    ोजा
    0.43
    닳
    0.42
     contracts
    0.42
     leasing
    0.42
    costcenter
    0.42
    努
    0.42
    ्वान
    0.41
    defaults
    0.40
    POSITIVE LOGITS
     Eggs
    0.87
    🥚
    0.84
     telur
    0.73
     eggs
    0.73
     Gesù
    0.71
     Egg
    0.71
    Eggs
    0.71
    鸡蛋
    0.71
     egg
    0.69
     Easter
    0.69
    Activations Density 0.179%

    No Known Activations