© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11449
    Prev
    Next
    INDEX
    Explanations

    type 2 diabetes or USB devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ورځې
    0.46
     comunicarse
    0.42
    цтва
    0.41
     يوم
    0.41
     cheerfully
    0.40
    versorgung
    0.40
    疹
    0.40
    否定
    0.38
     narcot
    0.38
    搜索引擎
    0.38
    POSITIVE LOGITS
     State
    0.46
     परिस्थित
    0.46
     Quality
    0.46
    iset
    0.44
     পড়ছে
    0.42
     Sart
    0.41
     Ork
    0.41
    irikan
    0.41
     নিয়ে
    0.40
     Theater
    0.40
    Activations Density 0.005%

    No Known Activations