© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109484
    Prev
    Next
    INDEX
    Explanations

    pronoun following 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_34/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
    她也
    -2.36
    她就
    -2.13
    她说
    -1.98
     они
    -1.86
    She
    -1.80
    但她
    -1.69
    她和
    -1.66
     ésta
    -1.66
    They
    -1.66
    彼女は
    -1.61
    POSITIVE LOGITS
     him
    9.44
     he
    5.38
     ему
    4.84
    他
    4.34
     his
    3.50
     ним
    3.45
    him
    3.39
    เขา
    3.28
     lui
    3.28
     them
    3.28
    Activations Density 0.133%

    No Known Activations