© 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. 80944
    Prev
    Next
    INDEX
    Explanations

    proper nouns and foreign names

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

    ruining the experience

    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
    ige
    0.47
    рг
    0.46
    ш
    0.43
    =',
    0.42
    itario
    0.41
    ("",
    0.40
     AJAX
    0.39
     ("
    0.38
    wiata
    0.38
     electromagnet
    0.38
    POSITIVE LOGITS
     dwóch
    0.49
    䢀
    0.49
    习近平
    0.47
     maß
    0.46
    čas
    0.46
     chwil
    0.46
    杨
    0.45
    ন্দে
    0.45
     частью
    0.45
    输出
    0.44
    Activations Density 0.001%

    No Known Activations