© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25175
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and associated items

    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
    Negative Logits
    animity
    -1.27
     these
    -1.27
    Beskrivning
    -1.25
    Inggris
    -1.24
     ſame
    -1.22
     laterales
    -1.22
     sejumlah
    -1.19
    总是
    -1.18
    ровании
    -1.16
     ++)
    -1.15
    POSITIVE LOGITS
     gdyż
    1.65
    -
    1.41
     only
    1.37
     answer
    1.32
    "
    1.31
    _
    1.26
    </h1>
    1.25
    都能
    1.22
     sole
    1.20
     inspiration
    1.20
    Activations Density 0.033%

    No Known Activations