© 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. 40296
    Prev
    Next
    INDEX
    Explanations

    early mid late periods

    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
     by
    -1.86
      
    -1.84
     outras
    -1.71
     classify
    -1.63
     regulate
    -1.59
    揶
    -1.59
     verifique
    -1.57
     relate
    -1.56
    such
    -1.55
    creating
    -1.55
    POSITIVE LOGITS
    w
    1.82
    也不
    1.75
     jotka
    1.65
     allemand
    1.64
    裊
    1.63
    鐿
    1.62
     prestaciones
    1.58
     hendak
    1.58
    噠
    1.58
    ława
    1.57
    Activations Density 0.018%

    No Known Activations