© 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. 53-GEMMASCOPE-2-RES-262K
    7. 8989
    Prev
    Next
    INDEX
    Explanations

    technical noun phrases

    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_53_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
     etc
    0.37
    之类的
    0.32
    等的
    0.31
    etc
    0.31
     ,
    0.27
     whatnot
    0.26
    等
    0.25
    など
    0.25
     coprime
    0.25
     usw
    0.24
    POSITIVE LOGITS
    apiUrl
    0.25
    ControlEvents
    0.23
     ხელისუფლების
    0.23
    doğan
    0.22
     gekommen
    0.22
    నాన్ని
    0.22
    rón
    0.22
    нена
    0.22
    પો
    0.21
    dbContext
    0.21
    Activations Density 0.663%

    No Known Activations