© 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. 10-GEMMASCOPE-RES-131K
    7. 44906
    Prev
    Next
    INDEX
    Explanations

    Ghanaian names and figures

    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
    Espero
    -1.88
     eve
    -1.77
     когда
    -1.77
    tól
    -1.74
     altre
    -1.66
    zehn
    -1.66
    ierten
    -1.62
    ÁN
    -1.62
     nemoc
    -1.61
    嚟
    -1.61
    POSITIVE LOGITS
     ecclesias
    1.77
     хочет
    1.67
    埽
    1.66
     devoid
    1.62
     that
    1.56
    $
    1.55
     slated
    1.55
     هایی
    1.53
     oceano
    1.53
     whose
    1.51
    Activations Density 0.003%

    No Known Activations