© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32024
    Prev
    Next
    INDEX
    Explanations

    dating and social connections

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

    diplomatic history and maturity

    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
    에서는
    0.48
     단순히
    0.47
     কেবলমাত্র
    0.47
     испы
    0.47
    があり
    0.44
    POWER
    0.44
     அனுமதிக்க
    0.44
    뒷
    0.44
     केवल
    0.43
     hurry
    0.43
    POSITIVE LOGITS
     diplomatic
    0.49
     multilateral
    0.40
    [![
    0.40
    جاد
    0.39
     diplomat
    0.39
    ("[
    0.38
    {.
    0.38
    ,!
    0.38
    zl
    0.37
    ]*
    0.37
    Activations Density 0.000%

    No Known Activations