© 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. 34-GEMMASCOPE-RES-131K
    7. 66352
    Prev
    Next
    INDEX
    Explanations

    ATP Synthase or ATPase

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

    scientific/technical terminology related to biochemistry, particularly mentions of ATP and enzyme complexes.

    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_34/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
    ouser
    -0.77
    楼主
    -0.75
    dbh
    -0.75
     navideñas
    -0.75
     COMPOUNDS
    -0.73
     secundarios
    -0.73
     Essentials
    -0.73
     navideños
    -0.71
     collègues
    -0.70
    smoke
    -0.70
    POSITIVE LOGITS
     Underground
    1.08
     monsters
    1.04
     underground
    1.02
     monster
    1.02
     barrier
    1.01
     Dre
    1.00
     SOUL
    0.98
     Chara
    0.94
     goat
    0.94
    Howdy
    0.93
    Activations Density 0.009%

    No Known Activations