© 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. 34-GEMMASCOPE-RES-131K
    4. 59109
    Prev
    Next
    INDEX
    Explanations

    possessive followed by pets

    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
    children
    -0.98
    ーブル
    -0.78
    zte
    -0.74
    tah
    -0.74
    まとめて
    -0.73
    лью
    -0.73
    alyptus
    -0.72
    CONTEN
    -0.71
    trials
    -0.70
    istration
    -0.69
    POSITIVE LOGITS
     dogs
    3.13
     dog
    2.59
    Dogs
    1.94
    dogs
    1.88
     cats
    1.84
     Dogs
    1.80
     pets
    1.70
    Dog
    1.60
     Dog
    1.54
    犬
    1.52
    Activations Density 0.036%

    No Known Activations