© 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. 86747
    Prev
    Next
    INDEX
    Explanations

    And yes

    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
    2
    -2.14
    3
    -2.02
     will
    -1.76
     завжди
    -1.71
     now
    -1.69
     both
    -1.66
    6
    -1.63
    9
    -1.61
    1
    -1.60
    8
    -1.55
    POSITIVE LOGITS
    MultipartFile
    1.52
     ihan
    1.48
    ℉
    1.38
    硖
    1.35
    ſtra
    1.35
    vábbi
    1.33
    LocalDate
    1.33
    xmlhttp
    1.31
     Arkivert
    1.31
    IImage
    1.29
    Activations Density 0.141%

    No Known Activations