© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13441
    Prev
    Next
    INDEX
    Explanations

    Bur

    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
    뛰
    0.61
    違う
    0.53
    異なる
    0.52
    Ext
    0.50
    futures
    0.50
     동시에
    0.50
     любви
    0.49
    oiden
    0.49
    VH
    0.49
    疇
    0.48
    POSITIVE LOGITS
     bur
    1.10
     BUR
    0.91
    Bur
    0.89
     Bur
    0.88
     Burlington
    0.72
    bur
    0.71
    geoning
    0.70
    lesque
    0.70
     Burke
    0.69
     Burton
    0.67
    Activations Density 0.019%

    No Known Activations