© 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. 34-GEMMASCOPE-RES-131K
    4. 80821
    Prev
    Next
    INDEX
    Explanations

    give or provide

    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
     explications
    -0.89
    ⃝
    -0.89
     invitar
    -0.87
     infrastruktur
    -0.86
     umo
    -0.86
    tapi
    -0.83
     ANNOUNC
    -0.82
    acknowled
    -0.82
     позволяет
    -0.82
     beton
    -0.81
    POSITIVE LOGITS
     offer
    3.34
     provide
    3.27
     offering
    3.02
     give
    2.95
     providing
    2.77
    提供
    2.63
     offers
    2.61
     giving
    2.61
     memberikan
    2.45
     gives
    2.41
    Activations Density 0.103%

    No Known Activations