© 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. 119648
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun context

    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
     I
    -2.34
     Our
    -2.02
    -
    -1.88
     focuses
    -1.77
    ?
    -1.77
    –
    -1.72
     about
    -1.71
     e
    -1.64
    .
    -1.64
     me
    -1.60
    POSITIVE LOGITS
     poitrine
    1.70
     desain
    1.57
     gardien
    1.55
     Teknologi
    1.52
     vété
    1.50
     postale
    1.50
    ቍ
    1.50
    錞
    1.49
    Качество
    1.49
     douceur
    1.48
    Activations Density 0.036%

    No Known Activations