© 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. 119842
    Prev
    Next
    INDEX
    Explanations

    e.g

    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
    </b>
    -2.05
     cũng
    -1.98
     also
    -1.77
    </th>
    -1.72
     також
    -1.61
     επίσης
    -1.56
     JUGA
    -1.55
    ˬ
    -1.55
     it
    -1.48
     between
    -1.46
    POSITIVE LOGITS
    .
    1.53
     mancher
    1.51
     proble
    1.48
     chilena
    1.46
     kimdir
    1.42
     réellement
    1.42
     hiasan
    1.41
     Aktiv
    1.41
    
    1.40
     kompatibel
    1.39
    Activations Density 0.057%

    No Known Activations