© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100693
    Prev
    Next
    INDEX
    Explanations

    full

    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
     tomando
    -2.22
            
    -1.97
    :
    -1.95
          
    -1.94
     The
    -1.90
     siguen
    -1.90
     often
    -1.87
     to
    -1.82
    -1.81
    一些
    -1.78
    POSITIVE LOGITS
    呖
    2.33
    蹓
    2.14
    飈
    2.09
     dizaines
    1.99
    錞
    1.98
     fermer
    1.95
    赈
    1.95
    Pgina
    1.94
    culares
    1.91
    锒
    1.91
    Activations Density 0.009%

    No Known Activations