© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47787
    Prev
    Next
    INDEX
    Explanations

    refrigerant, refrigeration, compressor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    water
    0.41
    Animals
    0.41
    Water
    0.40
    animals
    0.40
    лото
    0.39
    Filtered
    0.39
    갸
    0.38
    水
    0.38
     aguas
    0.38
    Baba
    0.37
    POSITIVE LOGITS
     refrigerant
    1.53
     Refriger
    1.30
     refriger
    1.27
     refrigeration
    1.23
     réfrig
    1.06
     Compressor
    1.02
     compressor
    1.00
     refrigerator
    0.97
    friger
    0.95
     холоди
    0.93
    Activations Density 0.024%

    No Known Activations