© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8064
    Prev
    Next
    INDEX
    Explanations

    features and qualities

    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
    今日
    -1.73
    昨日
    -1.59
    女性
    -1.55
    方法
    -1.50
    新
    -1.47
    我们
    -1.45
     interessiert
    -1.45
    Ǔ
    -1.45
    irtschaft
    -1.43
    　　（
    -1.42
    POSITIVE LOGITS
     such
    1.59
    说不定
    1.55
     —
    1.38
     include
    1.37
    也会
    1.36
    也會
    1.35
     but
    1.34
     -
    1.34
     เพื่อ
    1.33
    ようですが
    1.33
    Activations Density 0.019%

    No Known Activations