© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123695
    Prev
    Next
    INDEX
    Explanations

    technical units or identifiers starting with mb

    np_acts-logits-general · gemini-2.5-flash-lite

    the sequence "mb" followed by digits or in technical contexts like file names, variable names, or abbreviations (such as megabytes).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necessárias
    -2.95
    
    -2.67
    懨
    -2.59
    蛱
    -2.52
    führt
    -2.48
     måske
    -2.45
    衚
    -2.42
    縂
    -2.38
    屨
    -2.33
     córdoba
    -2.31
    POSITIVE LOGITS
    www
    2.56
    I
    2.53
    able
    2.41
    她就
    2.39
     Evidently
    2.25
    ка
    2.25
     detract
    2.20
    section
    2.17
     Maintaining
    2.14
     руке
    2.14
    Activations Density 0.004%

    No Known Activations