© 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. 34-GEMMASCOPE-RES-131K
    7. 106399
    Prev
    Next
    INDEX
    Explanations

    liquid nitrogen and cryogenics

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

    mentions of extremely low temperatures, cryogenic substances, or freezing processes.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    tidal
    -0.78
     Dalai
    -0.72
    engarkan
    -0.71
    ட்டு
    -0.70
     watermark
    -0.69
     Ridge
    -0.69
    閣
    -0.68
     Leaven
    -0.68
     BLM
    -0.66
     DAG
    -0.66
    POSITIVE LOGITS
     liquid
    2.34
     cry
    2.22
    liquid
    1.94
    Liquid
    1.87
     cryo
    1.84
     nitrogen
    1.82
     Liquid
    1.79
    cry
    1.73
     Cry
    1.66
     LN
    1.55
    Activations Density 0.052%

    No Known Activations