© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    demonstrates or illustrates

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

    demonstrate

    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
    </caption>
    0.38
     opge
    0.38
    괵
    0.38
    нду
    0.36
     dring
    0.35
    apparition
    0.35
     осторо
    0.35
    気になる
    0.34
    సర
    0.34
    懇
    0.34
    POSITIVE LOGITS
     demonstrates
    2.97
     demuestra
    2.66
     demonstrate
    2.61
     demonstrating
    2.61
     dimost
    2.58
     illustrates
    2.39
     demostrar
    2.34
     demost
    2.33
     демонстри
    2.25
     illustrate
    2.14
    Activations Density 0.262%

    No Known Activations