© 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. 76653
    Prev
    Next
    INDEX
    Explanations

    Alex Ferguson, Peter Schmeichel, Terry Tolkin

    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
    ビア
    -0.75
    renia
    -0.74
    걔
    -0.73
     sĩ
    -0.71
    vés
    -0.70
     Cau
    -0.69
    Adapters
    -0.69
     binh
    -0.69
     okt
    -0.68
     cau
    -0.68
    POSITIVE LOGITS
    粥
    0.88
     Passengers
    0.75
     Patrice
    0.75
     MUT
    0.75
    IRM
    0.75
     Fergus
    0.74
     legendary
    0.73
    🐡
    0.71
     infest
    0.71
     Carrington
    0.71
    Activations Density 0.010%

    No Known Activations