© 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. 101923
    Prev
    Next
    INDEX
    Explanations

    European institutional texts

    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
    '));
    -2.19
    </u>
    -2.19
    𓋼
    -2.05
    </i>
    -1.99
    ଞ
    -1.95
     These
    -1.84
    ();
    -1.84
    娛
    -1.80
     הוא
    -1.79
    ioneer
    -1.78
    POSITIVE LOGITS
    ኧ
    2.19
    觚
    2.13
    糁
    2.02
    摃
    1.97
     手機
    1.96
    ついた
    1.95
     rigorously
    1.93
    轳
    1.88
    
    1.88
     utili
    1.87
    Activations Density 0.010%

    No Known Activations