© 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. 10-GEMMASCOPE-RES-131K
    4. 87011
    Prev
    Next
    INDEX
    Explanations

    the start of sentences

    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
     of
    -1.50
    ↵↵↵
    -1.39
    ↵↵↵↵↵
    -1.34
    5
    -1.34
    ↵↵↵↵
    -1.34
    ↵↵↵↵↵↵
    -1.32
    ↵↵↵↵↵↵↵
    -1.18
    listair
    -1.16
     by
    -1.16
    ınd
    -1.14
    POSITIVE LOGITS
     their
    1.67
     saca
    1.37
     мають
    1.37
    their
    1.36
     berikan
    1.32
    could
    1.32
     adesivo
    1.29
    奩
    1.27
     have
    1.27
     Kč
    1.26
    Activations Density 0.188%

    No Known Activations