© 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. 71227
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

    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
     
    -2.05
    ↵↵
    -1.73
    就可以
    -1.56
    -1.48
    <em>
    -1.45
    <u>
    -1.40
    要素
    -1.40
     ‘
    -1.39
    ка
    -1.38
    “
    -1.38
    POSITIVE LOGITS
    鼉
    1.79
     our
    1.77
     the
    1.77
     innych
    1.69
     فنا
    1.66
     other
    1.66
     @}
    1.65
    嚯
    1.65
     diğer
    1.63
    Mittwoch
    1.52
    Activations Density 0.004%
    No Known Activations