© 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. 11786
    Prev
    Next
    INDEX
    Explanations

    look forward to

    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
     pocas
    -1.69
     STILL
    -1.65
     zweiter
    -1.63
     nunmehr
    -1.63
     soothe
    -1.60
     bajas
    -1.59
     rufen
    -1.59
    偌
    -1.59
     permissible
    -1.52
     schein
    -1.50
    POSITIVE LOGITS
    蛱
    1.46
    an
    1.41
     eisen
    1.40
    鸶
    1.38
     estadounid
    1.37
     vectorstock
    1.34
    ties
    1.33
    ée
    1.30
    这
    1.30
    การ
    1.29
    Activations Density 0.011%

    No Known Activations