© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9082
    Prev
    Next
    INDEX
    Explanations

    FSA' Sch affer Ö ncü ey's

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

    URL link structure

    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_40_width_16k_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
     "','"
    0.49
    丫
    0.40
     συν
    0.40
    件事
    0.39
     huidige
    0.39
    管理的
    0.39
    न्दावन
    0.38
     усіх
    0.38
    šć
    0.38
     Ανακτήθηκε
    0.38
    POSITIVE LOGITS
     possibilities
    0.40
     хотелось
    0.40
    ──
    0.40
     subray
    0.39
     dea
    0.39
    fromRGB
    0.39
     phénom
    0.39
     dépassant
    0.39
    ุง
    0.38
    .«
    0.38
    Activations Density 0.686%

    No Known Activations