© 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. 102390
    Prev
    Next
    INDEX
    Explanations

    phrases with following words

    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
     propriétés
    -1.52
     bienfaits
    -1.48
     myös
    -1.38
     papiers
    -1.34
    Increased
    -1.34
    他们
    -1.33
    这些
    -1.30
     նաև
    -1.29
     recettes
    -1.29
    improving
    -1.28
    POSITIVE LOGITS
     will
    2.13
     to
    1.83
     eventually
    1.49
    でしたね
    1.34
    ที่จะ
    1.34
    了一
    1.32
     likely
    1.30
     ultimately
    1.30
     tomorrow
    1.29
     helped
    1.28
    Activations Density 0.138%

    No Known Activations