© 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. 101844
    Prev
    Next
    INDEX
    Explanations

    possessives / 's followed by nouns

    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
    derdag
    -2.17
    媵
    -2.09
    鯓
    -1.88
    モア
    -1.88
    }$
    -1.86
     are
    -1.80
     pierws
    -1.79
    
    -1.75
    ჱ
    -1.75
    给出
    -1.75
    POSITIVE LOGITS
    '
    2.61
     a
    1.80
    Begriff
    1.78
    /
    1.73
    </strong>
    1.70
    (?)
    1.70
    (!)
    1.63
     tht
    1.63
    Various
    1.60
    荭
    1.59
    Activations Density 0.006%

    No Known Activations