© 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. 34-GEMMASCOPE-RES-131K
    7. 32875
    Prev
    Next
    INDEX
    Explanations

    possessive forms and contractions

    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_34/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
     gravy
    -0.78
     Hindi
    -0.75
    拣
    -0.74
    Chorus
    -0.73
     більше
    -0.71
    ían
    -0.71
     IEnumerable
    -0.71
    align
    -0.71
    tamide
    -0.71
     gets
    -0.70
    POSITIVE LOGITS
     contractions
    1.23
     contraction
    1.19
     apost
    1.13
    aujourd
    0.93
     possessive
    0.92
    collo
    0.91
     hasn
    0.90
     contracted
    0.89
     possession
    0.88
     EVOLUTION
    0.87
    Activations Density 0.042%

    No Known Activations