© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 928
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun "our"

    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
     когда
    -1.49
     observación
    -1.49
     recomendación
    -1.48
    鸲
    -1.48
     Presidencia
    -1.48
    だらけ
    -1.47
     одного
    -1.46
    鈊
    -1.45
    我們
    -1.43
     distinción
    -1.43
    POSITIVE LOGITS
    m
    1.97
    t
    1.67
    </h3>
    1.64
    k
    1.62
    f
    1.56
    v
    1.55
    ):
    1.55
    ve
    1.52
    l
    1.51
     =
    1.50
    Activations Density 0.034%

    No Known Activations