© 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. 325
    Prev
    Next
    INDEX
    Explanations

    separating clauses with punctuation

    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
     βιβ
    -1.66
     takich
    -1.57
    Such
    -1.56
     vandens
    -1.55
    bular
    -1.54
     όπως
    -1.50
     Method
    -1.50
     ceea
    -1.49
     tercih
    -1.47
     estos
    -1.46
    POSITIVE LOGITS
     was
    1.83
     became
    1.41
    ！　
    1.41
     has
    1.34
    ！(
    1.32
    1.28
     helped
    1.21
     but
    1.20
    magazin
    1.20
    !（
    1.19
    Activations Density 0.162%

    No Known Activations