© 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. 21628
    Prev
    Next
    INDEX
    Explanations

    capillary action and suction

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

    levitation, squeezing, floatation

    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
     Frieden
    0.47
    スタンダ
    0.47
    ソロ
    0.42
    锵
    0.41
    unud
    0.41
     geven
    0.41
     meneg
    0.41
    लिप
    0.41
     mwen
    0.40
    Czechoslovakia
    0.40
    POSITIVE LOGITS
     alarm
    0.44
    碾
    0.43
     공급
    0.42
     gallons
    0.42
    allery
    0.42
    Alarm
    0.41
     شركة
    0.41
     pipeline
    0.41
    pipeline
    0.41
    管道
    0.40
    Activations Density 0.001%

    No Known Activations