© 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. 10-GEMMASCOPE-RES-131K
    4. 19597
    Prev
    Next
    INDEX
    Explanations

    once in a opportunity

    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
     bestehenden
    -1.20
     étaient
    -1.20
     sorella
    -1.18
     favoriser
    -1.17
     diriger
    -1.16
     tendremos
    -1.15
    prehension
    -1.13
    вушка
    -1.13
     entsprechenden
    -1.13
    esai
    -1.12
    POSITIVE LOGITS
     for
    1.54
     opportunity
    1.37
     when
    1.32
     esses
    1.23
     потом
    1.22
    beforeAll
    1.21
     потім
    1.20
     mellan
    1.13
    Spesifikasi
    1.13
     if
    1.12
    Activations Density 0.029%

    No Known Activations