© 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. 67132
    Prev
    Next
    INDEX
    Explanations

    passing exams and tests

    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
     he
    -1.84
    \
    -1.68
    ikusbot
    -1.45
    夫妇
    -1.37
     is
    -1.36
    噜
    -1.34
    即是
    -1.34
     urllib
    -1.31
     ????
    -1.31
    ・・。
    -1.30
    POSITIVE LOGITS
     originalen
    1.53
     akhirnya
    1.52
     també
    1.47
    我们
    1.47
    igens
    1.45
     Fakta
    1.43
     Manfaat
    1.42
     dasarnya
    1.40
     identitas
    1.40
     Lingkungan
    1.39
    Activations Density 0.034%

    No Known Activations