© 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. 6321
    Prev
    Next
    INDEX
    Explanations

    She, women, shelf

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

    she sheets shepherd shelter

    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
    𒄑
    0.38
    脘
    0.38
    ırma
    0.37
    Ἰ
    0.35
     يناير
    0.34
     দারি
    0.34
    灸
    0.34
    㗊
    0.34
    යි
    0.33
    ື
    0.33
    POSITIVE LOGITS
     ше
    3.67
     SHE
    3.25
    SHE
    3.16
     Ше
    3.16
     शे
    3.11
    シェ
    2.95
     She
    2.88
    She
    2.78
    ше
    2.75
     シェ
    2.72
    Activations Density 0.172%

    No Known Activations