© 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. 59336
    Prev
    Next
    INDEX
    Explanations

    prepositions and punctuation

    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
    où
    -1.59
    where
    -1.47
    תּ
    -1.35
    퐿
    -1.34
    辛い
    -1.33
     donde
    -1.32
     saque
    -1.30
    cL
    -1.29
    つけて
    -1.28
     condenado
    -1.28
    POSITIVE LOGITS
     like
    1.73
     some
    1.70
     all
    1.62
     that
    1.57
     one
    1.54
     will
    1.53
     but
    1.48
     then
    1.48
     any
    1.44
     their
    1.39
    Activations Density 0.053%

    No Known Activations