© 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. 22066
    Prev
    Next
    INDEX
    Explanations

    museums and history exhibits

    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
     biasanya
    -1.39
     in
    -1.33
    kommt
    -1.14
     besonder
    -1.09
     serisi
    -1.05
     pada
    -1.05
    攞
    -1.02
     unless
    -1.00
     çünkü
    -1.00
     обычно
    -0.99
    POSITIVE LOGITS
     about
    1.30
    四年
    1.23
     kutoka
    1.23
     cucchiai
    1.22
    iclo
    1.18
     "','
    1.16
     μὲν
    1.16
     diverso
    1.13
    Beneficios
    1.13
    かは
    1.09
    Activations Density 0.068%

    No Known Activations