© 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. 10-GEMMASCOPE-RES-131K
    7. 66119
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their belongings

    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
     verminder
    -1.76
     niego
    -1.70
     เขา
    -1.64
     něj
    -1.63
     fuper
    -1.60
    ᕱ
    -1.60
     territoriale
    -1.58
     borse
    -1.56
     kommunik
    -1.56
     italie
    -1.55
    POSITIVE LOGITS
     we
    2.02
     after
    1.80
     only
    1.78
     may
    1.77
     can
    1.65
     a
    1.63
     might
    1.63
    ”
    1.63
    "
    1.62
    }{
    1.60
    Activations Density 0.014%

    No Known Activations