© 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. 31-GEMMASCOPE-2-RES-16K
    7. 4976
    Prev
    Next
    INDEX
    Explanations

    pressure, gas, expansion, ventilators

    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_16k_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
     سمیت
    0.50
     مشتری
    0.48
     সবার
    0.48
    জাতি
    0.47
     রশ্ম
    0.47
    谢
    0.46
    名单
    0.46
    apixel
    0.45
    玷
    0.45
     янва
    0.44
    POSITIVE LOGITS
     pressure
    1.09
     pneumatic
    1.05
     pressurized
    1.03
     gas
    1.00
    pressure
    0.98
     compressed
    0.97
     pneum
    0.95
     Pressure
    0.94
    Pressure
    0.94
     gases
    0.93
    Activations Density 0.331%

    No Known Activations