© 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. 9445
    Prev
    Next
    INDEX
    Explanations

    my possessive pronouns

    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
    They
    -1.66
    それは
    -1.60
     they
    -1.56
     mereka
    -1.55
     harten
    -1.49
    它们
    -1.43
    swire
    -1.43
    Mereka
    -1.42
     möjlighet
    -1.40
    他们
    -1.36
    POSITIVE LOGITS
     to
    2.13
     about
    1.80
    ’)
    1.52
     of
    1.50
     яго
    1.41
    しており
    1.41
    irsten
    1.40
     rid
    1.40
     pivotal
    1.39
    ’,
    1.38
    Activations Density 0.045%

    No Known Activations