© 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. 159
    Prev
    Next
    INDEX
    Explanations

    communication statuses and messages

    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
     různých
    -1.69
    ERVIEW
    -1.63
    bagian
    -1.58
     Abschied
    -1.58
     великолеп
    -1.57
    龊
    -1.57
     použí
    -1.57
    菝
    -1.55
    Če
    -1.54
     pensado
    -1.53
    POSITIVE LOGITS
    ться
    1.93
    on
    1.57
    al
    1.56
    などで
    1.55
    um
    1.55
     huid
    1.52
    it
    1.51
    ков
    1.47
    ner
    1.46
    ed
    1.43
    Activations Density 0.014%

    No Known Activations