© 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. 22-GEMMASCOPE-RES-131K
    4. 9516
    Prev
    Next
    INDEX
    Explanations

    giving or receiving

    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_22/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
    Сыртқы
    -0.93
     Белару
    -0.90
    jinal
    -0.88
    ogical
    -0.83
     homenagem
    -0.83
     Accesorios
    -0.82
    Secondo
    -0.81
    wegian
    -0.80
     traducciones
    -0.79
     déchets
    -0.77
    POSITIVE LOGITS
     delivering
    1.42
     delivery
    1.41
     offering
    1.40
     deliver
    1.24
     offer
    1.22
     providing
    1.12
     delivered
    1.11
     delivers
    1.05
     offers
    1.03
    Offering
    1.02
    Activations Density 0.108%

    No Known Activations