© 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. 68902
    Prev
    Next
    INDEX
    Explanations

    colloids, zymogen, Rxns, Brig

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

    scientific and technical terms in academic papers and research contexts.

    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
     maïs
    -1.09
     nk
    -1.05
     allerede
    -1.05
     aio
    -1.04
     sogenannten
    -1.03
     ongeveer
    -1.03
    олові
    -1.02
     bukanlah
    -1.02
     officiels
    -1.02
     ▶
    -1.00
    POSITIVE LOGITS
     first
    1.17
     there
    1.07
    :
    1.02
    财富
    1.00
     each
    0.98
    FlatButton
    0.98
     has
    0.94
     feedback
    0.94
     Jahrhunderts
    0.93
     only
    0.92
    Activations Density 0.017%

    No Known Activations