© 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. 67477
    Prev
    Next
    INDEX
    Explanations

    phrase "i'd say"

    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
     What
    -1.73
     не
    -1.69
     в
    -1.64
    ↵↵
    -1.62
     $\
    -1.60
     на
    -1.58
     but
    -1.58
     so
    -1.56
     –
    -1.52
    }{
    -1.48
    POSITIVE LOGITS
     mauva
    1.67
    嫑
    1.65
    ⵈ
    1.59
    涠
    1.55
     zelfs
    1.51
     uſed
    1.51
     upwards
    1.50
     faſt
    1.48
    全体的に
    1.48
     ſta
    1.47
    Activations Density 0.009%

    No Known Activations