© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-65K
    4. 1080
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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_40_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
     and
    0.13
     list
    0.13
    Data
    0.13
     (
    0.13
      
    0.12
     o
    0.12
     STR
    0.12
     con
    0.12
     high
    0.12
     CAP
    0.12
    POSITIVE LOGITS
     tagReport
    0.15
     캐릭터
    0.13
     ಖರೀದ
    0.13
     نماز
    0.13
     మహిళ
    0.13
     치료
    0.13
     thoſe
    0.13
     computeEncoder
    0.13
    )+"]("+
    0.13
     관광
    0.13
    Activations Density 1.178%

    No Known Activations