© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6180
    Prev
    Next
    INDEX
    Explanations

    Eastern Orthodox

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

    orch / ord / orbit

    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
    anesulfonyl
    0.42
     veya
    0.39
     tasmim
    0.37
     Kupfer
    0.37
    泮
    0.36
     nebo
    0.36
    藜
    0.36
     በመ
    0.35
    沛
    0.35
    嘜
    0.35
    POSITIVE LOGITS
     ор
    3.27
     Orth
    3.05
     orth
    3.03
     ort
    2.94
    Orth
    2.92
     Ort
    2.86
     Ор
    2.84
     Ordinance
    2.84
     ortho
    2.83
     ordinance
    2.81
    Activations Density 0.182%

    No Known Activations