© 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. 224999
    Prev
    Next
    INDEX
    Explanations

    Dulaglutide, enchanting, joint

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

    splash too much

    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
     смогут
    0.52
    Nuestro
    0.50
     миллиар
    0.48
    lineNumber
    0.45
     сможет
    0.44
    ה
    0.44
     Viceroy
    0.44
     incluidos
    0.44
     возбу
    0.44
     podríamos
    0.44
    POSITIVE LOGITS
    噸
    0.51
    の水
    0.48
     Water
    0.46
    acti
    0.46
    trusive
    0.44
     misconception
    0.44
    頑
    0.44
     રહે
    0.43
     Moderate
    0.43
    水
    0.43
    Activations Density 0.000%

    No Known Activations