© 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. 113175
    Prev
    Next
    INDEX
    Explanations

    solve, located, placed, approach, gallery, easier

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

    discriminator, Leader

    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
    мина
    0.53
    iciencia
    0.53
    кор
    0.52
    рида
    0.52
    ка
    0.50
    баров
    0.50
    полни
    0.50
     改
    0.49
    кир
    0.49
    кара
    0.48
    POSITIVE LOGITS
     Lymph
    0.49
     breast
    0.49
     lym
    0.48
     ब्रेस्ट
    0.47
    March
    0.46
    }\
    0.45
    edes
    0.44
    ถึง
    0.44
    Lymph
    0.44
     clade
    0.43
    Activations Density 0.001%

    No Known Activations