© 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. 40616
    Prev
    Next
    INDEX
    Explanations

    introduction to an explanation

    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
     of
    -2.66
     and
    -2.53
    鋇
    -1.96
     ilyen
    -1.95
    ",
    -1.80
     seluruh
    -1.77
     medición
    -1.73
     is
    -1.70
    </td>
    -1.69
    </b>
    -1.67
    POSITIVE LOGITS
     falschen
    1.61
     essentially
    1.54
    どういう
    1.53
    T
    1.52
     basically
    1.52
    
    1.49
    刧
    1.48
     jajaja
    1.48
     primarily
    1.48
     mainly
    1.48
    Activations Density 0.030%

    No Known Activations