© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89955
    Prev
    Next
    INDEX
    Explanations

    breakfast ingredients and dishes

    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
     mosquitos
    -0.79
     Popcorn
    -0.77
     SQU
    -0.75
    HDMI
    -0.75
     Margherita
    -0.74
    מא
    -0.73
    Xbox
    -0.73
     Snacks
    -0.72
     xenon
    -0.71
     hume
    -0.71
    POSITIVE LOGITS
     hash
    1.20
     potatoes
    1.16
    hash
    0.96
     Hash
    0.88
    Potatoes
    0.83
    Hash
    0.79
     Potatoes
    0.78
     home
    0.78
     these
    0.77
     Southern
    0.75
    Activations Density 0.017%

    No Known Activations