© 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. 32624
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and adjectives

    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
     cinza
    -1.42
     nô
    -1.39
     GETS
    -1.38
     lã
    -1.38
     volvió
    -1.37
     první
    -1.35
    摃
    -1.34
     trám
    -1.33
     撮り
    -1.32
     MAKES
    -1.32
    POSITIVE LOGITS
    P
    1.43
    S
    1.43
    L
    1.41
     even
    1.41
     has
    1.41
     Quite
    1.36
     had
    1.34
     undeniably
    1.34
     dramatically
    1.34
    F
    1.34
    Activations Density 0.306%

    No Known Activations