© 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. 13958
    Prev
    Next
    INDEX
    Explanations

    quantities and comparisons

    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
     sambil
    -1.70
     imprescin
    -1.55
     damski
    -1.54
     męski
    -1.51
    -1.47
     môžete
    -1.46
     Entdecken
    -1.45
     not
    -1.44
     żół
    -1.43
     selaku
    -1.43
    POSITIVE LOGITS
    臯
    2.06
     
    1.61
    祧
    1.58
     policia
    1.56
     português
    1.55
    找个
    1.55
    呖
    1.55
     rodo
    1.53
     dozen
    1.53
    见识
    1.51
    Activations Density 0.322%
    No Known Activations