© 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. 98244
    Prev
    Next
    INDEX
    Explanations

    investigations of drug effects

    np_acts-logits-general · gemini-2.5-flash-lite

    the end of scientific sentences, particularly in academic abstracts where periods are followed by new sentence starters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    tya
    -1.16
    ølge
    -1.05
     ⇒
    -0.98
     Staates
    -0.96
    ťou
    -0.96
    entown
    -0.96
    omato
    -0.96
    Ǻ
    -0.94
     everybody
    -0.94
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.94
    POSITIVE LOGITS
     Therefore
    1.24
     Consequently
    1.08
     therefore
    1.08
    Litteratur
    1.05
     поэтому
    1.05
    However
    1.03
    因此
    1.02
     thus
    1.02
     However
    1.02
     recently
    1.01
    Activations Density 0.833%

    No Known Activations