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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32520
    Prev
    Next
    INDEX
    Explanations

    Santa's light shines

    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_262k_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
    𝚊
    0.54
     ಹಾಗೂ
    0.48
     اسے
    0.47
    '،
    0.47
     ו
    0.46
    ୬
    0.45
    ა
    0.44
    тись
    0.44
     एवं
    0.44
    ниці
    0.44
    POSITIVE LOGITS
     Santa
    0.47
    ad
    0.46
    ară
    0.46
    ará
    0.43
    y
    0.43
    aram
    0.43
    red
    0.43
    las
    0.43
    ar
    0.42
    Santa
    0.41
    Activations Density 0.001%

    No Known Activations