© 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. 150948
    Prev
    Next
    INDEX
    Explanations

    for gold and brick

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

    stocks and investments fluctuate

    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
     Superintendent
    0.49
     ভারপ্রাপ্ত
    0.47
    是什麼
    0.47
    虚拟机
    0.45
     Predictions
    0.44
    剔
    0.44
    殄
    0.44
     Prosec
    0.44
     Multiplication
    0.43
    INST
    0.43
    POSITIVE LOGITS
     membres
    0.48
     HOP
    0.46
    ヘ
    0.46
    াহিত
    0.46
     хе
    0.45
     அவர்
    0.44
     workouts
    0.44
    an
    0.44
     clim
    0.44
    puts
    0.44
    Activations Density 0.000%

    No Known Activations