© 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. 210848
    Prev
    Next
    INDEX
    Explanations

    weigh in, weigh up, weigh out, weigh whether

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

    assigning weights

    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
     esophagus
    0.50
     땅
    0.49
     обита
    0.48
    어로
    0.47
    supset
    0.47
     गेम्स
    0.47
    solved
    0.47
     éton
    0.46
    っています
    0.45
    仁
    0.45
    POSITIVE LOGITS
     Weight
    1.09
     weigh
    1.00
     weight
    0.98
     WEIGHT
    0.98
     weighs
    0.96
    权重
    0.95
     Weighted
    0.94
    Weight
    0.93
    weight
    0.91
    weights
    0.90
    Activations Density 0.044%

    No Known Activations