© 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. 55980
    Prev
    Next
    INDEX
    Explanations

    pronouns in dative case

    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
    arla
    -0.88
     sizi
    -0.85
    NOON
    -0.81
    irlo
    -0.81
    ço
    -0.78
    ㄥ
    -0.76
    RTSC
    -0.74
    delaide
    -0.73
    Herkunft
    -0.73
     ihn
    -0.72
    POSITIVE LOGITS
     вам
    3.17
     ему
    2.48
     Вам
    2.45
     vám
    2.39
     нам
    2.39
     тебе
    2.27
     Ihnen
    2.25
     आपको
    1.96
     ей
    1.88
     ihnen
    1.87
    Activations Density 0.029%

    No Known Activations