© 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. 121674
    Prev
    Next
    INDEX
    Explanations

    tickets, terrorist, laws, story

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

    diagrams and clustering

    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
     janela
    0.47
     ín
    0.45
     esperan
    0.45
     possibilidade
    0.45
    s
    0.45
     offen
    0.45
    ढ़ाई
    0.44
     rohk
    0.44
    ﹑
    0.43
     posibilidad
    0.43
    POSITIVE LOGITS
    ikhil
    0.49
    MQ
    0.48
    puts
    0.47
    iska
    0.46
    মূলক
    0.46
    imm
    0.45
    irteen
    0.45
    ptic
    0.45
    atee
    0.45
     تقل
    0.45
    Activations Density 0.001%

    No Known Activations