© 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. 62700
    Prev
    Next
    INDEX
    Explanations

    refrigerant

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     cancel
    -0.70
    мую
    -0.69
     Gu
    -0.69
    File
    -0.69
    ="@
    -0.67
    有意思
    -0.67
    厚
    -0.66
     rain
    -0.66
    bés
    -0.65
     talked
    -0.65
    POSITIVE LOGITS
     refrigerant
    1.83
     Refriger
    1.58
    refriger
    1.51
     refriger
    1.48
    Refriger
    1.38
     REFR
    1.37
     refrigeration
    1.19
    냉
    1.10
    yf
    0.99
     fluor
    0.97
    Activations Density 0.021%

    No Known Activations