© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23358
    Prev
    Next
    INDEX
    Explanations

    refrigerant and environmental impact

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

    refrigerant compounds and compressors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    抚
    0.49
    ิจ
    0.48
     pInBuffer
    0.46
    酱
    0.46
     সারি
    0.45
     सॉ
    0.43
     рит
    0.43
    晠
    0.43
    тием
    0.43
     патри
    0.43
    POSITIVE LOGITS
     refrigerant
    1.14
     refriger
    1.05
     refrigeration
    0.97
     Refriger
    0.95
     ozone
    0.76
     refrigerated
    0.74
     réfrig
    0.73
     frigor
    0.72
     Ozone
    0.67
     refrigerator
    0.67
    Activations Density 0.032%

    No Known Activations