© 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. 124590
    Prev
    Next
    INDEX
    Explanations

    sentence and phrase beginnings

    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
     certamente
    -1.50
     frequentemente
    -1.41
     generalmente
    -1.37
     leopardo
    -1.37
     pétrole
    -1.35
     têm
    -1.32
     praticamente
    -1.31
     normalmente
    -1.30
     multiuso
    -1.30
    either
    -1.28
    POSITIVE LOGITS
     At
    1.55
    什么呢
    1.46
     as
    1.40
     As
    1.40
    At
    1.38
     In
    1.36
     llamaba
    1.30
     revital
    1.30
     Making
    1.28
     bylo
    1.27
    Activations Density 0.023%

    No Known Activations