© 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. 738
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

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

    disclaimers and explanations

    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
     J
    0.42
     Kh
    0.42
     ख
    0.40
    Kh
    0.39
     جس
    0.39
     Ka
    0.38
     Kre
    0.38
     Les
    0.37
     Y
    0.37
     Kobayashi
    0.37
    POSITIVE LOGITS
    Jean
    0.40
    蚪
    0.40
    чи
    0.39
    ွဲ
    0.38
    णसी
    0.37
    cje
    0.37
     courbe
    0.36
    ນະ
    0.36
    encie
    0.35
     aparelho
    0.35
    Activations Density 0.083%

    No Known Activations