© 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. 42122
    Prev
    Next
    INDEX
    Explanations

    slash or international characters

    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
     Because
    -1.88
    Because
    -1.55
    because
    -1.50
     because
    -1.48
     with
    -1.40
     Lingkungan
    -1.36
    When
    -1.31
    MINUTES
    -1.25
     complained
    -1.25
     According
    -1.22
    POSITIVE LOGITS
    /"
    1.59
    élection
    1.59
     EVEN
    1.43
    ;"
    1.43
    眨眼
    1.42
    ⮑
    1.41
    
    1.41
     "
    1.41
    玏
    1.40
     hefty
    1.39
    Activations Density 0.069%

    No Known Activations