© 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. 7013
    Prev
    Next
    INDEX
    Explanations

    and terrace

    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
     träd
    -0.81
    Beispiele
    -0.77
    點
    -0.77
    tranh
    -0.75
     退
    -0.74
    attore
    -0.74
    ݿ
    -0.74
     Otros
    -0.73
     jednocześnie
    -0.73
    Willi
    -0.73
    POSITIVE LOGITS
     построе
    0.84
    welling
    0.81
     niveau
    0.81
    taa
    0.81
     ۲۰۰
    0.79
    SPIR
    0.78
    regulation
    0.78
     №
    0.78
     Uno
    0.76
    าสตร์
    0.76
    Activations Density 0.004%

    No Known Activations