© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86090
    Prev
    Next
    INDEX
    Explanations

    things to do and activities

    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
     quieren
    -1.59
     proporcionan
    -1.51
    稣
    -1.50
     wydaj
    -1.49
     слишком
    -1.48
    ètre
    -1.48
    tividade
    -1.46
     chiedere
    -1.45
     baterie
    -1.44
     dekoratif
    -1.44
    POSITIVE LOGITS
     in
    2.06
     throughout
    1.33
     echter
    1.27
     ("
    1.24
     культура
    1.23
    岌
    1.23
     않았
    1.20
    vape
    1.20
    XXV
    1.19
    chtes
    1.17
    Activations Density 0.022%

    No Known Activations