© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123919
    Prev
    Next
    INDEX
    Explanations

    code elements and related phrases

    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
    The
    -1.78
    <blockquote>
    -1.78
    only
    -1.66
    ressible
    -1.62
    Now
    -1.61
    U
    -1.61
     年级
    -1.59
    In
    -1.59
    So
    -1.59
    像
    -1.58
    POSITIVE LOGITS
    </strong>
    2.86
    齜
    1.94
    )
    1.79
    鰨
    1.77
    ܖ
    1.66
     solchen
    1.64
    廝
    1.61
    </h1>
    1.60
    瓛
    1.59
    izoen
    1.56
    Activations Density 0.000%

    No Known Activations