© 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. 43425
    Prev
    Next
    INDEX
    Explanations

    their / they / themselves

    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
    ᚑ
    -1.62
     vostra
    -1.55
     only
    -1.45
     ему
    -1.43
    诲
    -1.41
     his
    -1.39
     njego
    -1.38
     такого
    -1.36
     jego
    -1.35
    ondale
    -1.34
    POSITIVE LOGITS
     themselves
    3.66
     their
    2.31
    themselves
    2.17
     leurs
    1.98
     they
    1.84
    they
    1.82
     Their
    1.80
     THEY
    1.73
    selves
    1.70
    their
    1.66
    Activations Density 1.438%

    No Known Activations