© 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. 22-GEMMASCOPE-RES-131K
    7. 131040
    Prev
    Next
    INDEX
    Explanations

    references, numbers, Q:

    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_22/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
     vélos
    -1.02
     its
    -1.01
     boî
    -0.99
    ]}>
    -0.99
     シーン
    -0.96
    쇼
    -0.96
    entri
    -0.96
     integran
    -0.94
    捗
    -0.88
    meanor
    -0.87
    POSITIVE LOGITS
    ！！！！
    1.02
    ！！！！！
    0.94
    isler
    0.94
    不然
    0.93
     дітей
    0.90
     congressional
    0.90
     credere
    0.89
     chiesto
    0.88
     richiesto
    0.86
    <0xDB>
    0.85
    Activations Density 0.000%

    No Known Activations