© 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. 23736
    Prev
    Next
    INDEX
    Explanations

    Christmas Nativity baby child carols

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

    newborn king Christmas

    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
    ́
    0.44
     abhid
    0.43
    clap
    0.42
    腋
    0.42
    PLASMA
    0.41
    кру
    0.41
    ட்டாக
    0.40
    自我
    0.40
     PLASMA
    0.40
    omie
    0.40
    POSITIVE LOGITS
     Christmas
    1.01
    Christmas
    1.01
     क्रिसमस
    0.97
     Weihnachts
    0.92
     Weihnacht
    0.91
    圣诞
    0.87
     christmas
    0.86
    christmas
    0.85
    🎄
    0.85
     Weihn
    0.85
    Activations Density 0.042%

    No Known Activations