© 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. 58786
    Prev
    Next
    INDEX
    Explanations

    quantity manipulation

    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
    鬭
    -2.86
     但
    -2.66
     glän
    -2.39
     schicken
    -2.31
     ſever
    -2.31
    仅
    -2.28
     exclusivamente
    -2.28
     seminal
    -2.25
    を用
    -2.22
     klassische
    -2.20
    POSITIVE LOGITS
    呖
    3.30
    ஂ
    3.14
    ၟ
    2.89
    .
    2.80
    ⤥
    2.78
    ⚋
    2.78
    ſelves
    2.77
    ֟
    2.72
    蝙
    2.69
    媖
    2.67
    Activations Density 0.012%

    No Known Activations