© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15632
    Prev
    Next
    INDEX
    Explanations

    micro- followed by various terms

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

    prefixes "micro-" that modify or classify terms in technical, medical, or technological contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Negative Logits
     most
    -1.30
    ± 
    -1.28
     with
    -1.13
     depending
    -1.13
     Most
    -1.09
     Meningkatkan
    -1.08
     beliebtesten
    -1.06
     about
    -1.05
    natura
    -1.05
     Also
    -1.05
    POSITIVE LOGITS
    小时
    1.28
    micro
    1.17
    atta
    1.17
     otor
    1.13
    entist
    1.12
    Micro
    1.11
     micro
    1.09
     Headphones
    1.09
     Bathroom
    1.09
    hender
    1.08
    Activations Density 0.165%

    No Known Activations