© 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. 103937
    Prev
    Next
    INDEX
    Explanations

    recipe, adapted, scaling recipes

    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
    CultureInfo
    -0.89
     donuts
    -0.86
     bladder
    -0.85
    UV
    -0.84
     cappuccino
    -0.82
    discount
    -0.82
     ikiwa
    -0.81
     stimulus
    -0.80
     porridge
    -0.80
    憔
    -0.80
    POSITIVE LOGITS
     recipe
    1.07
     adapted
    1.02
     cordón
    0.98
     Recipe
    0.96
     Adapted
    0.93
     ада
    0.91
    adapted
    0.91
     دستور
    0.91
    Scaling
    0.90
    Adapted
    0.90
    Activations Density 0.023%

    No Known Activations