© 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. 12548
    Prev
    Next
    INDEX
    Explanations

    business dealings and operations

    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
     세포
    0.49
    ט
    0.46
    ༸
    0.45
    調理
    0.40
    Ć
    0.39
    imbing
    0.39
    idescent
    0.39
    细胞
    0.38
     טי
    0.38
    粿
    0.37
    POSITIVE LOGITS
     undertakings
    0.45
     advertisers
    0.43
     endorsements
    0.42
     dealings
    0.42
     URLs
    0.40
     assets
    0.40
     incidental
    0.39
     infringing
    0.39
     newspapers
    0.38
     motels
    0.38
    Activations Density 0.015%

    No Known Activations