© 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. 45305
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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
     Алла
    -0.91
     milyen
    -0.91
     részt
    -0.88
    实际上
    -0.88
     ľ
    -0.88
     veľa
    -0.88
     segíts
    -0.87
     kezd
    -0.86
     cikk
    -0.86
    orche
    -0.85
    POSITIVE LOGITS
     perceived
    0.93
     renew
    0.89
     daily
    0.88
     proposta
    0.84
     hinder
    0.83
     labrador
    0.82
     Mexicano
    0.81
     regata
    0.81
     nunmehr
    0.81
    Vapour
    0.79
    Activations Density 0.013%

    No Known Activations