© 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. 44669
    Prev
    Next
    INDEX
    Explanations

    words before prepositions

    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
    の作品
    -1.48
    omorphisms
    -1.48
     mangá
    -1.44
    .~\
    -1.41
     there
    -1.40
     גם
    -1.40
     obti
    -1.37
     rodas
    -1.36
     indiví
    -1.34
     excelente
    -1.33
    POSITIVE LOGITS
     to
    1.65
     after
    1.40
     from
    1.37
     or
    1.34
     involucra
    1.27
     “
    1.26
     its
    1.23
    -
    1.21
     during
    1.18
     in
    1.16
    Activations Density 0.210%

    No Known Activations