© 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. 64354
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and associated nouns

    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
     their
    -3.06
     your
    -2.08
     an
    -2.02
     first
    -2.02
     all
    -1.97
     one
    -1.96
     not
    -1.93
     our
    -1.85
     by
    -1.83
     so
    -1.82
    POSITIVE LOGITS
     horri
    1.59
    ✔️
    1.52
    ることができます
    1.48
     Atención
    1.48
     هناك
    1.46
     🥰
    1.44
    ztes
    1.44
     expérimentés
    1.43
     Dinas
    1.41
    ፫
    1.39
    Activations Density 0.038%

    No Known Activations