© 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. 34-GEMMASCOPE-RES-131K
    7. 32094
    Prev
    Next
    INDEX
    Explanations

    initials followed by names

    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_34/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
     Player
    -0.81
     Nathan
    -0.80
     Past
    -0.79
     corrientes
    -0.78
    ystema
    -0.77
    нтів
    -0.75
     conceito
    -0.75
     développ
    -0.75
    になりたい
    -0.74
     collègues
    -0.73
    POSITIVE LOGITS
     other
    0.95
     autres
    0.91
    itemList
    0.80
    industria
    0.79
    Cloudy
    0.78
     annen
    0.77
     Hoc
    0.76
     Kongo
    0.75
     åp
    0.75
    зно
    0.75
    Activations Density 0.026%

    No Known Activations