© 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. 14675
    Prev
    Next
    INDEX
    Explanations

    anniversary birthday wedding

    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
     एकल
    0.56
     अस्वी
    0.54
    upra
    0.54
     nausea
    0.53
     pressão
    0.52
    阝
    0.52
    órz
    0.51
     ~$
    0.51
    ộ
    0.51
    avits
    0.50
    POSITIVE LOGITS
     anniversary
    3.78
     annivers
    3.53
     Anniversary
    3.50
     юбилей
    2.95
     centenary
    2.94
     юби
    2.92
     anniversaire
    2.84
     aniversario
    2.83
     celebrating
    2.78
     anivers
    2.78
    Activations Density 0.149%

    No Known Activations