© 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. 41-GEMMASCOPE-2-RES-262K
    7. 103215
    Prev
    Next
    INDEX
    Explanations

    apple pie, gastric cancer, Amazon Warehouse, Designated Nationals

    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_all/layer_41_width_262k_l0_big
    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
    icitis
    0.39
    ifan
    0.38
    อาการ
    0.36
    思考
    0.35
    Lon
    0.35
    Massachusetts
    0.34
    iyan
    0.34
    侕
    0.34
    해주세요
    0.33
    ytically
    0.33
    POSITIVE LOGITS
     unset
    0.45
     setUp
    0.43
     সামনে
    0.40
     exemplo
    0.39
     учреждения
    0.39
     esempio
    0.39
     uncovered
    0.39
    ங்கம்
    0.38
    িয়োগ
    0.38
     ОС
    0.38
    Activations Density 0.047%

    No Known Activations