© 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. 144929
    Prev
    Next
    INDEX
    Explanations

    World Bank, loans

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

    Persian strategy game terminology

    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
    Remark
    0.45
     драматур
    0.44
    <0xB5>
    0.42
    ธุ
    0.42
    りが
    0.42
    gist
    0.42
     خبرنگ
    0.42
    抠
    0.42
    Dragged
    0.41
    ifico
    0.41
    POSITIVE LOGITS
     hotels
    0.53
     Hotels
    0.52
     endings
    0.52
     users
    0.51
     IMPLEMENT
    0.51
     plans
    0.50
     Users
    0.48
     Procurement
    0.47
     loans
    0.46
     Nails
    0.46
    Activations Density 0.001%

    No Known Activations