© 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. 34-GEMMASCOPE-RES-131K
    7. 55868
    Prev
    Next
    INDEX
    Explanations

    a way to do something

    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_34/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
    下意识
    -1.02
    锢
    -1.01
     opportunità
    -1.00
     aliments
    -0.99
     carc
    -0.98
    说出
    -0.97
    opportunities
    -0.94
    过来了
    -0.93
    ₖ
    -0.93
    র্ব
    -0.92
    POSITIVE LOGITS
     ensure
    1.53
     approach
    1.52
     get
    1.48
     guarantee
    1.35
     Approach
    1.30
     avoid
    1.23
     combat
    1.15
     ensuring
    1.15
     quickly
    1.12
     Ensure
    1.12
    Activations Density 0.059%

    No Known Activations