© 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. 86817
    Prev
    Next
    INDEX
    Explanations

    renewable energy

    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
     cuyo
    -1.83
    ()]);
    -1.70
     esos
    -1.66
     upheaval
    -1.61
    𝙜
    -1.58
     groans
    -1.54
    ς
    -1.53
    食べ物
    -1.49
     derrot
    -1.48
    ()];
    -1.46
    POSITIVE LOGITS
    梣
    1.85
    攆
    1.74
     الأخرى
    1.71
    摃
    1.70
     judíos
    1.65
    ︲
    1.60
     antigüedad
    1.57
    木坂
    1.55
     continually
    1.48
     condições
    1.48
    Activations Density 0.012%

    No Known Activations