© 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-65K
    7. 2150
    Prev
    Next
    INDEX
    Explanations

    corporate brands and their products

    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
    藠
    0.32
     minuten
    0.31
     erythrocytes
    0.30
     عجیب
    0.30
    㫧
    0.30
     stillness
    0.30
     Auswirkungen
    0.30
    耖
    0.30
     interdiscipl
    0.29
     convexes
    0.29
    POSITIVE LOGITS
    ’
    0.44
    ®
    0.39
    旗下
    0.36
    '
    0.35
    公司的
    0.35
    Ⓡ
    0.34
     subsidiary
    0.33
    Corp
    0.33
     companies
    0.32
     ®
    0.32
    Activations Density 0.312%

    No Known Activations