© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10671
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns 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
     ‘’
    -1.88
    没办法
    -1.88
     («
    -1.79
     também
    -1.77
    鲧
    -1.75
    C
    -1.72
     tornillos
    -1.70
    リボン
    -1.67
     również
    -1.63
    Adap
    -1.60
    POSITIVE LOGITS
     Meningkatkan
    2.02
     to
    1.95
     }],
    1.82
    ruguay
    1.78
     all
    1.77
    })));
    1.70
     {
    
    
    1.65
    </em>
    1.63
     Penelitian
    1.59
    婚礼
    1.59
    Activations Density 0.033%

    No Known Activations