© 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. 14078
    Prev
    Next
    INDEX
    Explanations

    African

    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
    ENGLISH
    0.56
     ইংরেজি
    0.55
    ковский
    0.54
    ิมพ์
    0.53
    跨
    0.53
     negeri
    0.52
     legislación
    0.52
     ইংরেজ
    0.52
    庤
    0.51
    natives
    0.51
    POSITIVE LOGITS
     descent
    1.09
     descended
    1.06
     Descent
    0.96
     desc
    0.88
     descend
    0.82
     descends
    0.82
    ‑
    0.81
     descending
    0.80
     Desc
    0.79
     descendant
    0.78
    Activations Density 0.021%

    No Known Activations