© 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. 31-GEMMASCOPE-2-RES-262K
    7. 98667
    Prev
    Next
    INDEX
    Explanations

    FSC certification; Gatsby undoubtedly; children watched

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

    rise of the machines

    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_31_width_262k_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
    ’
    0.53
     night
    0.52
     merchants
    0.50
     (
    0.47
     o
    0.46
     transit
    0.45
    el
    0.45
     extraction
    0.44
     nor
    0.44
    x
    0.44
    POSITIVE LOGITS
    했는데
    0.51
    MatContext
    0.48
    సింది
    0.47
     المط
    0.46
     الفيزياء
    0.46
     الجرس
    0.46
     والج
    0.46
     atthakath
    0.46
     நடைபெற்ற
    0.45
     پڑھیئے
    0.45
    Activations Density 0.001%

    No Known Activations