© 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. 71330
    Prev
    Next
    INDEX
    Explanations

    an exercise in

    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
     has
    -1.98
    についての
    -1.57
     zonder
    -1.54
     caminhão
    -1.51
     such
    -1.50
     is
    -1.49
     jornalista
    -1.48
     the
    -1.47
     laikā
    -1.43
    赑
    -1.43
    POSITIVE LOGITS
    s
    1.70
    એ
    1.68
     exercise
    1.65
    Whether
    1.61
    abatic
    1.58
    美丽的
    1.57
    this
    1.55
     誰
    1.55
    úly
    1.48
    It
    1.45
    Activations Density 0.011%

    No Known Activations