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

    Neuronpedia

    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. 11584
    Prev
    Next
    INDEX
    Explanations

    holidays and events

    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
     collaborazione
    0.55
     camaraderie
    0.45
     partenariat
    0.44
     collaboration
    0.42
     Yung
    0.41
    掾
    0.41
     parceria
    0.41
    滏
    0.41
     colaboración
    0.41
     गतिविधियों
    0.40
    POSITIVE LOGITS
     Christmas
    0.85
     festivals
    0.82
     Thanksgiving
    0.81
    Christmas
    0.80
    ristmas
    0.79
     Xmas
    0.78
     Festival
    0.76
     christmas
    0.75
    Halloween
    0.75
     Weihn
    0.74
    Activations Density 0.139%

    No Known Activations