© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42043
    Prev
    Next
    INDEX
    Explanations

    defining attributes and properties

    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
    艄
    -1.90
     każdego
    -1.80
     ポーズ
    -1.80
    尛
    -1.66
    禤
    -1.63
    摃
    -1.63
    乆
    -1.60
    苼
    -1.59
    neſs
    -1.59
    industrie
    -1.58
    POSITIVE LOGITS
    .
    2.20
    k
    1.81
    b
    1.59
    1.55
    :
    1.53
     -
    1.50
    (
    1.49
    </h2>
    1.39
    a
    1.38
    od
    1.38
    Activations Density 0.010%

    No Known Activations