© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86151
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by requests

    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
     permette
    -1.51
     Unido
    -1.50
     able
    -1.43
    nables
    -1.30
    老婆
    -1.30
    婊
    -1.29
     możliwości
    -1.27
    必要な
    -1.27
     adet
    -1.26
     sidan
    -1.25
    POSITIVE LOGITS
     information
    1.45
    '
    1.32
    a
    1.31
     berwarna
    1.30
     after
    1.15
     Maybe
    1.13
     Either
    1.13
     Clearly
    1.11
    "
    1.10
     data
    1.09
    Activations Density 0.041%

    No Known Activations