© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14273
    Prev
    Next
    INDEX
    Explanations

    multilingual

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     its
    0.66
     mocked
    0.62
    Figs
    0.61
     conversion
    0.56
    Its
    0.55
     sprayed
    0.55
     =$
    0.55
     conversions
    0.54
     Figs
    0.54
     CDs
    0.54
    POSITIVE LOGITS
     доби
    0.55
    引起的
    0.55
    导致的
    0.54
    お知らせ
    0.53
    érist
    0.53
     أخ
    0.52
    akir
    0.50
     gradioApp
    0.50
     골
    0.48
    ucceeded
    0.48
    Activations Density 0.002%

    No Known Activations