© 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. 33568
    Prev
    Next
    INDEX
    Explanations

    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_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
     chré
    -1.80
     eccl
    -1.73
     religieuses
    -1.72
     religieux
    -1.64
    ığım
    -1.46
    Läs
    -1.41
     cukru
    -1.37
    mujeres
    -1.35
     chrétiens
    -1.35
    Tienen
    -1.34
    POSITIVE LOGITS
     our
    3.33
     we
    3.28
     nossas
    1.58
    our
    1.55
    ּוֹ
    1.52
     μας
    1.52
     unserer
    1.48
    我们
    1.48
     last
    1.47
     nostra
    1.45
    Activations Density 0.002%

    No Known Activations