© 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. 112219
    Prev
    Next
    INDEX
    Explanations

    in for , in store

    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
    Its
    -1.98
     \
    -1.70
     viena
    -1.63
     its
    -1.60
    \_
    -1.56
    D
    -1.56
     stedet
    -1.51
     zehn
    -1.48
    可不是
    -1.48
     vienas
    -1.45
    POSITIVE LOGITS
    
    1.81
    咵
    1.70
    蒾
    1.70
    ského
    1.63
    Ӝ
    1.57
    niveau
    1.55
    །
    1.54
    álva
    1.53
     những
    1.50
    ").
    1.49
    Activations Density 0.009%

    No Known Activations