© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102439
    Prev
    Next
    INDEX
    Explanations

    specific proper 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
     saranno
    -2.20
    饜
    -2.09
    茈
    -2.05
    㩒
    -2.02
    揷
    -1.98
     dacă
    -1.96
     vengono
    -1.96
    eſ
    -1.94
     verranno
    -1.91
    釹
    -1.91
    POSITIVE LOGITS
        
    2.11
    优秀
    1.94
    ৄ
    1.91
     AWESOME
    1.89
     ‘
    1.86
     Could
    1.84
     Either
    1.81
    R
    1.80
     cursory
    1.80
    有机
    1.77
    Activations Density 0.020%

    No Known Activations