© 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. 177308
    Prev
    Next
    INDEX
    Explanations

    harvest donations, consequences of, OBD-II, week under

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

    meeting occurs

    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
    罨
    0.51
    インド
    0.51
     защиты
    0.50
    牛肉
    0.49
    餃
    0.49
    ជាមួយ
    0.48
     করিয়াছি
    0.48
    飲食
    0.48
    Koch
    0.47
     thịt
    0.47
    POSITIVE LOGITS
    stration
    0.56
     a
    0.50
     Kes
    0.50
     USA
    0.49
     Quot
    0.49
    at
    0.49
    絊
    0.49
     Fab
    0.48
     Sunny
    0.48
     Vest
    0.48
    Activations Density 0.001%

    No Known Activations