© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 708
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     and
    -1.78
     in
    -1.59
    >();
    
    -1.56
    *}{
    -1.52
    愎
    -1.50
    五日
    -1.48
    ness
    -1.42
    cenzo
    -1.38
    istorante
    -1.38
    ściu
    -1.37
    POSITIVE LOGITS
     dibanding
    1.61
    槩
    1.60
    Regarding
    1.55
     "..\..\..\
    1.54
    Perhaps
    1.48
    خخ
    1.45
    Argu
    1.44
     jesús
    1.43
    Considering
    1.41
    是一個
    1.41
    Activations Density 0.056%

    No Known Activations