© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 89
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
    下来的
    -1.40
    erobic
    -1.34
     —
    -1.31
    了一会儿
    -1.31
     -
    -1.27
     ”
    -1.27
     not
    -1.26
     «
    -1.24
     to
    -1.23
    鹩
    -1.22
    POSITIVE LOGITS
    vají
    1.51
     если
    1.50
    fordshire
    1.48
     festen
    1.42
    prender
    1.42
     tutaj
    1.40
     jika
    1.38
    ixante
    1.34
     когда
    1.30
    ETO
    1.29
    Activations Density 0.376%

    No Known Activations