© 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. 99648
    Prev
    Next
    INDEX
    Explanations

    payments, including shopify

    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
     자주
    0.46
    슘
    0.45
     endothelium
    0.44
     안
    0.44
     सुप
    0.43
     polyphen
    0.43
    䂘
    0.43
    ͊
    0.43
     ethyl
    0.42
     oxid
    0.42
    POSITIVE LOGITS
    Including
    0.50
     imposes
    0.49
    galaxy
    0.48
     constitutes
    0.47
     prescribes
    0.47
    aue
    0.46
    的产品
    0.46
    тная
    0.46
     последнего
    0.46
    INCLUDING
    0.45
    Activations Density 0.000%

    No Known Activations