© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52464
    Prev
    Next
    INDEX
    Explanations

    egg, shells, protein

    np_acts-logits-general · gemini-2.5-flash-lite

    egg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    သွယ်
    0.56
    ബൈ
    0.48
    endaftaran
    0.47
    거리
    0.46
    Paradise
    0.46
    ጐ
    0.43
     거리
    0.43
     दुष्
    0.42
    iş
    0.41
    Celtic
    0.41
    POSITIVE LOGITS
    🥚
    1.47
     egg
    1.29
     Eggs
    1.29
     Egg
    1.27
     eggs
    1.26
    Egg
    1.15
    卵
    1.14
     अंडे
    1.12
    eggs
    1.11
     huevo
    1.10
    Activations Density 0.049%

    No Known Activations