© 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. 47710
    Prev
    Next
    INDEX
    Explanations

    joining organizations or groups

    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
    {
    -3.95
    ка
    -2.59
    </strong>
    -2.56
     everlasting
    -2.42
     adorable
    -2.38
     avalanche
    -2.33
     انگلیسی
    -2.27
     eminent
    -2.25
     popular
    -2.20
    蛧
    -2.14
    POSITIVE LOGITS
     joined
    3.22
    镚
    2.67
    媖
    2.50
    けれ
    2.44
    嗚
    2.42
    はこんな感じ
    2.36
     全新
    2.36
     Ráp
    2.34
     兒童
    2.33
     一九
    2.28
    Activations Density 0.008%

    No Known Activations