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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 39790
    Prev
    Next
    INDEX
    Explanations

    air compression temperature

    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_31_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
     書い
    0.51
    мила
    0.50
    trashItem
    0.46
    玷
    0.46
    امن
    0.46
    Alz
    0.46
     spineItem
    0.46
    Parm
    0.45
    셰
    0.45
     शशि
    0.44
    POSITIVE LOGITS
     gas
    1.07
     pneumatic
    1.05
     pneum
    1.00
     Pneum
    0.98
     gases
    0.95
     air
    0.93
     compressor
    0.91
    气体
    0.90
     Gas
    0.89
    gas
    0.86
    Activations Density 0.101%

    No Known Activations