© 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. 90418
    Prev
    Next
    INDEX
    Explanations

    New York Times publications

    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
    \
    -2.09
     verbessert
    -1.99
    tedì
    -1.95
     was
    -1.85
    GraphicsUnit
    -1.84
     (‘
    -1.84
    )’
    -1.80
    orsese
    -1.80
     bewegt
    -1.80
    );
    -1.77
    POSITIVE LOGITS
    儅
    2.14
    it
    1.98
    剮
    1.96
     banho
    1.92
    ஂ
    1.84
    桖
    1.83
     atentos
    1.81
     abiye
    1.78
    　　　　　　
    1.77
    ⑧
    1.76
    Activations Density 0.002%

    No Known Activations