© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101484
    Prev
    Next
    INDEX
    Explanations

    demonstrates, planet, classic, urgency

    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
     which
    0.53
    r
    0.52
     Naples
    0.50
     modernity
    0.49
     disdain
    0.48
     Fortune
    0.48
     নীচে
    0.48
     Downtown
    0.48
     Brentwood
    0.47
     British
    0.46
    POSITIVE LOGITS
    جه
    0.46
    щими
    0.46
    蠕
    0.46
    Ча
    0.44
    тру
    0.44
    дки
    0.43
    ຢ່າງ
    0.43
    종
    0.43
    الي
    0.43
    штар
    0.43
    Activations Density 0.002%

    No Known Activations