© 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. 59098
    Prev
    Next
    INDEX
    Explanations

    code structures and definitions

    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
    克服
    -0.85
     unless
    -0.82
     upon
    -0.80
     buhay
    -0.79
    thra
    -0.79
     {}
    -0.79
     Även
    -0.77
    澡
    -0.77
    illen
    -0.76
     голов
    -0.75
    POSITIVE LOGITS
     \%,
    0.87
     ドラ
    0.87
     kilka
    0.85
    žem
    0.84
    ίη
    0.84
    货币
    0.83
    IRQn
    0.82
     religieuse
    0.81
     meglio
    0.80
    andra
    0.78
    Activations Density 0.005%

    No Known Activations