© 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. 781
    Prev
    Next
    INDEX
    Explanations

    singleton pregnancies

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

    establishing credit or source code

    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
     галу
    0.52
     λόγω
    0.52
     বন্দ
    0.52
     然後
    0.51
     將
    0.50
     然后
    0.49
     কণ্ঠে
    0.49
     そして
    0.49
     найбільш
    0.49
     দশমিক
    0.48
    POSITIVE LOGITS
     élim
    0.54
     elim
    0.54
    p
    0.50
     Lind
    0.49
    m
    0.48
     imgs
    0.47
     C
    0.47
     Peanut
    0.46
    IB
    0.46
     for
    0.45
    Activations Density 0.000%

    No Known Activations