© 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. 28280
    Prev
    Next
    INDEX
    Explanations

    citations and email addresses

    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
    ↵↵↵
    -1.29
    ↵↵
    -1.23
    ↵↵↵↵
    -1.14
    ↵↵↵↵↵
    -1.09
    ↵↵↵↵↵↵
    -1.05
     of
    -1.04
     хотел
    -1.03
    ↵↵↵↵↵↵↵
    -1.02
     this
    -1.00
    なんですね
    -1.00
    POSITIVE LOGITS
    Soorten
    1.12
     parfü
    1.07
    ewel
    1.02
    がありますが
    1.02
    şk
    1.01
    олові
    1.00
    Occasion
    0.99
    Kenmerken
    0.98
    ेत्र
    0.98
     ORGANISM
    0.97
    Activations Density 0.001%

    No Known Activations