© 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. 196313
    Prev
    Next
    INDEX
    Explanations

    academic and research contexts

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

    designed to exploit

    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
     i
    0.62
     money
    0.51
     e
    0.49
    led
    0.45
     any
    0.45
     state
    0.45
     taxpayer
    0.45
     or
    0.45
    o
    0.45
     more
    0.44
    POSITIVE LOGITS
    团队
    0.53
     акаде
    0.53
     bioquímica
    0.52
     коллек
    0.50
    Gracias
    0.49
    BrNO
    0.48
    感谢
    0.48
     Ünivers
    0.47
     تیم
    0.46
     академи
    0.46
    Activations Density 0.000%

    No Known Activations