© 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. 13855
    Prev
    Next
    INDEX
    Explanations

    undefeated, unbeaten, or not defeated

    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
     '
    -2.06
      
    -1.91
    бина
    -1.81
    a
    -1.80
    せば
    -1.80
    ar
    -1.73
    1
    -1.70
     llave
    -1.69
    Ꮠ
    -1.66
    龵
    -1.66
    POSITIVE LOGITS
     untuk
    2.11
     there
    1.89
    ка
    1.80
     From
    1.76
    replyreport
    1.71
     conocía
    1.67
    לי
    1.65
     At
    1.63
    ра
    1.61
    There
    1.61
    Activations Density 0.006%

    No Known Activations