© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1628
    Prev
    Next
    INDEX
    Explanations

    fluid pressure and flow

    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
     політи
    0.70
     биографи
    0.68
     полити
    0.63
     سیاست
    0.59
     രാഷ്ട്രീയ
    0.58
    谋
    0.58
    琐
    0.58
     سیاسی
    0.57
     паліты
    0.57
    认
    0.57
    POSITIVE LOGITS
     pumps
    1.66
     pump
    1.60
     water
    1.59
     pumping
    1.53
     flow
    1.49
     tubing
    1.45
     airflow
    1.42
     pipes
    1.38
     valves
    1.37
     filtration
    1.37
    Activations Density 0.564%

    No Known Activations