© 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. 112670
    Prev
    Next
    INDEX
    Explanations

    GLP-1 receptor agonist

    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
     canoeing
    0.46
    sent
    0.46
    astro
    0.46
    ver
    0.44
    audio
    0.43
    ,
    0.43
     invaded
    0.43
     गाँ
    0.42
     chloroform
    0.42
    BO
    0.42
    POSITIVE LOGITS
    ෆ
    0.52
     alphan
    0.51
    𝐺
    0.49
    бри
    0.48
     ⭐
    0.47
    𝛼
    0.46
    섦
    0.46
    itäten
    0.45
    ром
    0.45
    ６
    0.45
    Activations Density 0.003%

    No Known Activations