© 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. 68296
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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
     rédu
    -1.54
     feront
    -1.51
     récentes
    -1.48
    躋
    -1.41
    がこの
    -1.39
     rév
    -1.38
    those
    -1.37
     renfor
    -1.36
     actuelles
    -1.33
    叼
    -1.33
    POSITIVE LOGITS
     about
    2.17
     in
    1.42
     first
    1.41
     --
    1.35
    －－
    1.34
     a
    1.31
     before
    1.26
     at
    1.24
     the
    1.23
     now
    1.20
    Activations Density 0.042%

    No Known Activations