© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17834
    Prev
    Next
    INDEX
    Explanations

    coronary occlusion

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

    oc or occ

    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_53_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
    湟
    0.40
    ﭔ
    0.39
     Kou
    0.38
    菀
    0.37
    theit
    0.36
    驢
    0.35
     분위
    0.34
     grantResults
    0.34
    进士
    0.34
    鲵
    0.34
    POSITIVE LOGITS
    OC
    2.78
    oc
    2.70
     OC
    2.66
    Oc
    2.58
     oc
    2.56
     Oc
    2.55
     Occ
    2.48
    Occ
    2.47
    OCC
    2.42
     OCC
    2.42
    Activations Density 0.272%

    No Known Activations