© 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. 5914
    Prev
    Next
    INDEX
    Explanations

    formal communication style

    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
     Supreme
    0.30
     ofthe
    0.30
    INA
    0.29
     fondly
    0.28
     \
    0.27
     weil
    0.27
     MongoClient
    0.27
     Sac
    0.27
    ,]
    0.27
     Combination
    0.26
    POSITIVE LOGITS
    ي
    0.30
    й
    0.29
    лдуу
    0.27
    ி
    0.27
     رسمی
    0.25
    ר
    0.25
    पणे
    0.25
    有问题
    0.24
     failings
    0.24
    τε
    0.23
    Activations Density 0.649%

    No Known Activations