© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179931
    Prev
    Next
    INDEX
    Explanations

    phrases following prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ਸ
    0.54
     ή
    0.51
     או
    0.51
     أو
    0.49
    或
    0.48
     или
    0.47
     ἢ
    0.47
    的情況
    0.46
    ﺔ
    0.46
     または
    0.46
    POSITIVE LOGITS
    generational
    0.44
     worldRank
    0.44
     jego
    0.42
     jaren
    0.41
     Parenthood
    0.41
     parenteral
    0.41
     deuter
    0.38
     Pathol
    0.38
    ≒
    0.38
     njegov
    0.38
    Activations Density 0.001%

    No Known Activations