© 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. 1711
    Prev
    Next
    INDEX
    Explanations

    plot aspects or story summaries

    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
    注意事
    -1.89
    heid
    -1.78
    ＊＊＊
    -1.74
    ⽼
    -1.73
    itisation
    -1.71
    ///////
    -1.67
    　　「
    -1.65
    ✽
    -1.64
    sprecher
    -1.60
    𝐖
    -1.60
    POSITIVE LOGITS
     хорошем
    2.06
     quint
    1.73
    -
    1.72
     translucent
    1.70
    '
    1.67
    她的
    1.67
    
    1.67
    しましたが
    1.65
     miniature
    1.63
    O
    1.61
    Activations Density 0.016%

    No Known Activations