© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48821
    Prev
    Next
    INDEX
    Explanations

    creating document elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    諌
    0.42
     thoughts
    0.39
     diagnosed
    0.38
     kiss
    0.38
    男朋友
    0.38
     sö
    0.37
     obtenido
    0.37
     fle
    0.37
     UNIV
    0.37
     symmetrical
    0.36
    POSITIVE LOGITS
    createElement
    0.83
     document
    0.65
    Document
    0.64
     $('<
    0.64
     документа
    0.63
    document
    0.62
     dokument
    0.59
    Doc
    0.58
     createElement
    0.58
    dokument
    0.58
    Activations Density 0.022%

    No Known Activations