© 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. 43734
    Prev
    Next
    INDEX
    Explanations

    software project structure

    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
     muestran
    -2.03
     herhangi
    -1.98
     necesitan
    -1.90
     siguen
    -1.82
     hacen
    -1.77
     pueden
    -1.76
     mantienen
    -1.74
     reciben
    -1.73
     hiçbir
    -1.72
     alcuni
    -1.69
    POSITIVE LOGITS
     honom
    1.79
    hibitions
    1.68
     夾
    1.66
     añ
    1.66
    Quite
    1.66
     Ottobre
    1.49
     eser
    1.49
    Ᏺ
    1.48
    ጺ
    1.48
     oktober
    1.47
    Activations Density 0.005%

    No Known Activations