© 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. 34-GEMMASCOPE-RES-131K
    7. 78057
    Prev
    Next
    INDEX
    Explanations

    Shen, Sheng, Schen, Schön names

    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
    時間が
    -0.75
    かえ
    -0.74
    highly
    -0.74
     précédentes
    -0.74
    뤄
    -0.72
     oldukça
    -0.71
    拙
    -0.71
    日が
    -0.69
     зае
    -0.69
    心が
    -0.68
    POSITIVE LOGITS
     Menon
    0.85
     沈
    0.82
     Shen
    0.82
    penn
    0.75
     tears
    0.75
     μην
    0.74
    Empty
    0.74
     identité
    0.72
     teeth
    0.71
     conviction
    0.71
    Activations Density 0.012%

    No Known Activations