© 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-65K
    7. 41048
    Prev
    Next
    INDEX
    Explanations

    Fantasy RPG, technology, or science concepts

    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_65k_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
     odorless
    0.46
    💮
    0.46
     ngok
    0.44
     cylinders
    0.44
    ソニック
    0.43
     металла
    0.43
     suitors
    0.42
     installing
    0.42
     LIGHT
    0.42
     snugly
    0.42
    POSITIVE LOGITS
     주문
    0.42
    ስቃ
    0.41
    㑹
    0.41
    都在
    0.40
    ？
    0.39
    湁
    0.39
    是否存在
    0.39
    掠
    0.39
    往
    0.39
     был
    0.38
    Activations Density 0.027%

    No Known Activations