© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 645
    Prev
    Next
    INDEX
    Explanations

    Imperial followed by nations or institutions

    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_34/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
     爪
    -0.93
    未来的
    -0.93
     Brag
    -0.90
    ラメ
    -0.87
    úč
    -0.87
     последу
    -0.86
     operação
    -0.85
    ドキュ
    -0.85
    滋賀
    -0.84
     COLOR
    -0.83
    POSITIVE LOGITS
     Imper
    1.16
    istic
    1.13
    Imper
    0.98
    imperial
    0.97
     imper
    0.91
     While
    0.85
    imper
    0.84
    理工
    0.82
    饋
    0.82
    istically
    0.81
    Activations Density 0.007%

    No Known Activations