© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85750
    Prev
    Next
    INDEX
    Explanations

    stock and stocking items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.39
    嘣
    -2.23
    т
    -2.23
    $
    -2.08
    ”،
    -2.08
    屺
    -2.06
     laajenta
    -2.03
    izophrenia
    -1.96
    The
    -1.90
    MessageTagHelper
    -1.89
    POSITIVE LOGITS
    います
    2.41
    Hanya
    2.08
    狁
    2.02
    鱨
    1.97
    0
    1.97
     теми
    1.96
    ༛
    1.93
     để
    1.91
    出かけ
    1.89
    eding
    1.86
    Activations Density 0.003%

    No Known Activations