© 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. 246
    Prev
    Next
    INDEX
    Explanations

    referring to lists or groups

    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
     demás
    -1.13
     other
    -1.11
    的其他
    -1.09
    อีก
    -1.02
     دیگر
    -0.99
    和其他
    -0.99
    комнат
    -0.97
    olingo
    -0.96
     Other
    -0.96
     otro
    -0.96
    POSITIVE LOGITS
     these
    3.13
     them
    2.55
     such
    2.50
     таких
    2.33
    這些
    2.28
     those
    2.25
     этих
    2.11
    这些
    2.03
    Such
    2.03
    these
    1.96
    Activations Density 0.200%

    No Known Activations