© 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. 60001
    Prev
    Next
    INDEX
    Explanations

    questions and technical keywords

    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
     him
    -1.70
    แรก
    -1.65
     нього
    -1.59
     вся
    -1.56
     puis
    -1.56
    b
    -1.55
     tries
    -1.55
     Of
    -1.52
     These
    -1.52
     There
    -1.52
    POSITIVE LOGITS
    呖
    2.02
     mereka
    1.95
     حتی
    1.94
     medan
    1.81
    媖
    1.80
    俢
    1.66
    媄
    1.64
     normaal
    1.63
     batterie
    1.62
    龶
    1.61
    Activations Density 0.144%

    No Known Activations