© 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. 22-GEMMASCOPE-RES-131K
    7. 84148
    Prev
    Next
    INDEX
    Explanations

    common nouns ending phrases

    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_22/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
    wiście
    -1.05
    ïd
    -1.03
     -"
    -0.99
    %.
    -0.98
     again
    -0.96
     eléctricos
    -0.96
    DIT
    -0.94
     japoneses
    -0.93
    itiers
    -0.91
     anymore
    -0.89
    POSITIVE LOGITS
     Since
    1.05
     so
    0.98
    cinco
    0.98
    Westfalen
    0.96
     Following
    0.94
    ఙ
    0.94
     Cruces
    0.94
    toda
    0.94
     بوده
    0.93
    ƣ
    0.93
    Activations Density 0.148%

    No Known Activations