© 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. 19814
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and comparisons

    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
     fetchData
    -1.20
     will
    -1.19
     dacă
    -1.18
    だよね
    -1.18
    ここから
    -1.14
    About
    -1.12
    よな
    -1.12
     need
    -1.12
     примеру
    -1.12
     tehdä
    -1.10
    POSITIVE LOGITS
     other
    1.43
    athons
    1.40
     });
    1.39
    ORUS
    1.23
     many
    1.23
    soka
    1.22
     any
    1.22
    tholes
    1.20
    tifiable
    1.20
    èmes
    1.17
    Activations Density 0.435%

    No Known Activations