© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7791
    Prev
    Next
    INDEX
    Explanations

    producer/consumer/Publisher relationships

    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
    ↵
    -1.80
     first
    -1.68
     навіть
    -1.50
     accented
    -1.50
     estadounidenses
    -1.47
     ‘‘
    -1.42
     bewilder
    -1.41
    čnega
    -1.41
    ні
    -1.41
    ឬ
    -1.38
    POSITIVE LOGITS
     From
    1.84
     We
    1.73
     mať
    1.60
    だったので
    1.49
     With
    1.47
     จาก
    1.46
    leurs
    1.45
     môžete
    1.43
     And
    1.40
     zowel
    1.40
    Activations Density 0.011%

    No Known Activations