© 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. 101400
    Prev
    Next
    INDEX
    Explanations

    you to

    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
     einem
    -2.09
    इटम
    -1.95
    2
    -1.91
    </em>
    -1.82
     зді
    -1.73
    ↵
    -1.71
    他に
    -1.70
     you
    -1.65
     zwei
    -1.60
     gdyż
    -1.60
    POSITIVE LOGITS
    夘
    1.89
     télécommande
    1.88
    ,
    1.84
     Songtext
    1.84
     ſou
    1.80
     TAMB
    1.80
     oliveira
    1.75
     Princesa
    1.74
     PUST
    1.72
     AGUA
    1.71
    Activations Density 0.028%

    No Known Activations