© 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. 48306
    Prev
    Next
    INDEX
    Explanations

    who and which

    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
     for
    -1.73
    fordshire
    -1.66
     that
    -1.52
    ==",
    -1.52
    ಠ
    -1.48
    aspectj
    -1.41
    шт
    -1.40
    {
    -1.38
    tolua
    -1.38
    },
    -1.37
    POSITIVE LOGITS
    を選び
    1.77
    
    1.62
    を選
    1.57
    该如何
    1.53
     fonctionnent
    1.52
     surtido
    1.50
    听见
    1.48
    Metode
    1.45
    綑
    1.45
    を選ぶ
    1.45
    Activations Density 0.111%

    No Known Activations