© 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. 71191
    Prev
    Next
    INDEX
    Explanations

    ENABLE, 最新, 最近

    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
    镦
    -3.13
    毉
    -2.89
    栊
    -2.75
    휀
    -2.73
    樒
    -2.73
     水彩
    -2.72
    
    -2.70
    嫪
    -2.69
    栳
    -2.67
     夜景
    -2.66
    POSITIVE LOGITS
    -
    3.56
     zehn
    2.89
     就
    2.66
    2
    2.64
     需要
    2.55
    A
    2.53
     …
    2.52
    C
    2.48
    Q
    2.47
     größeren
    2.42
    Activations Density 0.001%

    No Known Activations