© 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. 22-GEMMASCOPE-RES-131K
    7. 72772
    Prev
    Next
    INDEX
    Explanations

    pronoun reference

    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_22/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
     mnoho
    -0.89
     entire
    -0.88
     Tro
    -0.87
     stránka
    -0.87
    Especially
    -0.87
    adaan
    -0.86
    ünstler
    -0.85
     especially
    -0.85
     encontrarás
    -0.85
     particular
    -0.84
    POSITIVE LOGITS
     it
    3.03
     its
    1.50
    它
    1.47
     esso
    1.46
    それを
    1.46
    それが
    1.42
     them
    1.28
     celui
    1.23
    把它
    1.19
     його
    1.15
    Activations Density 0.189%

    No Known Activations