© 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. 1090
    Prev
    Next
    INDEX
    Explanations

    originally published or posted

    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
     The
    -2.19
    eſ
    -2.17
     связанные
    -2.03
    “
    -1.95
    них
    -1.93
     comin
    -1.92
     refugiados
    -1.92
     if
    -1.92
    ᝢ
    -1.91
     mutfak
    -1.89
    POSITIVE LOGITS
     they
    1.99
    Disclaimer
    1.91
    ing
    1.89
    我很
    1.87
    Originally
    1.87
    我先
    1.84
    鸶
    1.80
    actéristi
    1.79
    ,”
    1.77
    ſſen
    1.77
    Activations Density 0.004%

    No Known Activations