© 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. 133059
    Prev
    Next
    INDEX
    Explanations

    bail, bond, legal release

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

    Wealth Management, Religious Perspectives, Predetermined events

    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
    бург
    0.52
     bur
    0.51
     e
    0.47
    uy
    0.46
     calves
    0.46
     comte
    0.45
    bur
    0.45
    prof
    0.44
    ma
    0.44
     bourgeoisie
    0.44
    POSITIVE LOGITS
     lézards
    0.54
    輕鬆
    0.52
     দরকার
    0.52
    添付
    0.49
    આત
    0.49
    階段
    0.49
     सादर
    0.49
    胼
    0.49
    عاد
    0.47
     नांद
    0.47
    Activations Density 0.001%

    No Known Activations