© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97768
    Prev
    Next
    INDEX
    Explanations

    publication date

    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
    ícil
    -0.95
    aClass
    -0.91
     behaves
    -0.89
     Messing
    -0.88
     prenda
    -0.85
     cabina
    -0.82
     polisi
    -0.82
     Decorations
    -0.79
     Behaviors
    -0.77
    میزی
    -0.77
    POSITIVE LOGITS
     Next
    0.88
     He
    0.85
     OUT
    0.81
     gen
    0.80
     Dynamic
    0.79
    guang
    0.77
     projects
    0.76
     Quality
    0.75
     According
    0.75
    clectic
    0.75
    Activations Density 0.011%

    No Known Activations