© 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. 22-GEMMASCOPE-RES-131K
    4. 10824
    Prev
    Next
    INDEX
    Explanations

    numerical descriptions

    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_22/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
    dây
    -1.70
    ַּ
    -1.64
     during
    -1.54
    erobic
    -1.51
    ִּ
    -1.49
    ֶּ
    -1.46
    ּוֹ
    -1.42
     erity
    -1.39
     indicó
    -1.38
    写真を撮
    -1.37
    POSITIVE LOGITS
     mesmas
    1.75
     ἀ
    1.53
    ׇ
    1.48
     meninas
    1.42
    ophanes
    1.38
    ۱۶
    1.38
     Siapa
    1.34
     Jezus
    1.34
     cidades
    1.31
     primeiras
    1.30
    Activations Density 0.009%

    No Known Activations